diff --git a/cache/aggregate_scoress_cache_7b814a45375ad6b75add8b396f69c2cd.csv b/cache/aggregate_scoress_cache_7b814a45375ad6b75add8b396f69c2cd.csv new file mode 100644 index 0000000000000000000000000000000000000000..6a6a793708b8e63b456190f5081b2353677e28f6 --- /dev/null +++ b/cache/aggregate_scoress_cache_7b814a45375ad6b75add8b396f69c2cd.csv @@ -0,0 +1,72 @@ +model,score +gpt_4o_2024_05_13,0.9950869236583522 +gpt_4_turbo_2024_04_09,0.9639153609872332 +gpt_4_0125_preview,0.9393939393939394 +claude_3_opus_20240229,0.9220898724004315 +yi_large_preview,0.8845096932053453 +llama3.1_70b_instruct,0.8832459207459207 +qwen2_72b_instruct,0.8719243719243719 +gpt_4_0613,0.8648074952422778 +gemma_2_27b_it,0.8510517260517261 +llama3_70b_instruct,0.849670938694048 +mistral_large,0.8470006184291898 +yi_1.5_34b_chat,0.7714889277389277 +llama3_70b,0.7611156781553201 +claude_3_sonnet_20240229,0.7541101640480523 +mixtral_8x22b_instruct_v0.1,0.7425976800976801 +qwen1.5_110b_chat,0.7320934784170079 +mistral_medium,0.7056277056277057 +phi_3_medium_4k_instruct,0.696301247771836 +qwen1.5_32b_chat,0.6812609659248315 +claude_3_haiku_20240307,0.6757563807253248 +mistral_large_2402,0.6705753184014054 +qwen1.5_72b,0.6692868451728518 +qwen1.5_72b_chat,0.6604933136636727 +command_r_plus,0.6508289415898112 +yi_34b,0.6270777876367939 +phi_3_mini_4k_instruct,0.6218470721621983 +gemma_2_9b_it,0.6216006216006217 +qwen1.5_32b,0.6175551742436105 +llama_2_70b,0.585811187829169 +gpt_3.5_turbo_0125,0.5795841063698206 +yi_34b_chat,0.5793988997113997 +gemini_1.0_pro,0.5205318491032778 +gpt_3.5_turbo_0613,0.5196837944664031 +llama3_8b_instruct,0.5166348882210227 +yi_1.5_9b_chat,0.5150335775335776 +qwen2_7b_instruct,0.4803418803418803 +phi_3_mini_128k_instruct,0.47774531890678346 +mixtral_8x7b_instruct_v0.1,0.47245816635618004 +starling_lm_7b_beta,0.46037960638800973 +qwen1.5_14b_chat,0.45760855624301 +tulu_2_dpo_70b,0.44326821637746006 +llama3.1_8b_instruct,0.4429972804972805 +command_r,0.42476786498525626 +openhermes_2.5_mistral_7b,0.4133219954648526 +mistral_7b_instruct_v0.2,0.38528271156947624 +yi_1.5_6b_chat,0.3616155902920609 +llama_2_70b_chat,0.3429423284465301 +starling_lm_7b_alpha,0.3192125334982478 +llama3_8b,0.3191327255539897 +gemma_1.1_7b_it,0.3093664233370116 +zephyr_7b_beta,0.3012633624878523 +qwen1.5_7b,0.29290520556048505 +gemma_7b,0.29047416067876425 +vicuna_33b_v1.3,0.28480038480038483 +qwen1.5_7b_chat,0.27333417049803604 +llama_2_13b,0.2660179289106947 +mistral_7b_instruct_v0.3,0.21805555555555559 +yi_6b_chat,0.20091647770219198 +yi_6b,0.19687349577512162 +qwen1.5_4b,0.16834733893557421 +vicuna_7b_v1.5,0.14973544973544975 +gemma_7b_it,0.14039115646258504 +qwen1.5_4b_chat,0.14036924293526934 +phi_2,0.1326664119754182 +llama_2_7b_chat,0.11841995751468631 +gemma_1.1_2b_it,0.09431689342403628 +llama_2_7b,0.06859327581964463 +qwen1.5_1.8b_chat,0.06363517629273932 +gemma_2b,0.05727290916366547 +olmo_7b,0.011775543550753635 +qwen1.5_0.5b_chat,0.008163265306122448 diff --git a/cache/aggregate_scoress_cache_bdd8d629730630ed8e73cb56f53f335b.csv b/cache/aggregate_scoress_cache_bdd8d629730630ed8e73cb56f53f335b.csv new file mode 100644 index 0000000000000000000000000000000000000000..6a6a793708b8e63b456190f5081b2353677e28f6 --- /dev/null +++ b/cache/aggregate_scoress_cache_bdd8d629730630ed8e73cb56f53f335b.csv @@ -0,0 +1,72 @@ +model,score +gpt_4o_2024_05_13,0.9950869236583522 +gpt_4_turbo_2024_04_09,0.9639153609872332 +gpt_4_0125_preview,0.9393939393939394 +claude_3_opus_20240229,0.9220898724004315 +yi_large_preview,0.8845096932053453 +llama3.1_70b_instruct,0.8832459207459207 +qwen2_72b_instruct,0.8719243719243719 +gpt_4_0613,0.8648074952422778 +gemma_2_27b_it,0.8510517260517261 +llama3_70b_instruct,0.849670938694048 +mistral_large,0.8470006184291898 +yi_1.5_34b_chat,0.7714889277389277 +llama3_70b,0.7611156781553201 +claude_3_sonnet_20240229,0.7541101640480523 +mixtral_8x22b_instruct_v0.1,0.7425976800976801 +qwen1.5_110b_chat,0.7320934784170079 +mistral_medium,0.7056277056277057 +phi_3_medium_4k_instruct,0.696301247771836 +qwen1.5_32b_chat,0.6812609659248315 +claude_3_haiku_20240307,0.6757563807253248 +mistral_large_2402,0.6705753184014054 +qwen1.5_72b,0.6692868451728518 +qwen1.5_72b_chat,0.6604933136636727 +command_r_plus,0.6508289415898112 +yi_34b,0.6270777876367939 +phi_3_mini_4k_instruct,0.6218470721621983 +gemma_2_9b_it,0.6216006216006217 +qwen1.5_32b,0.6175551742436105 +llama_2_70b,0.585811187829169 +gpt_3.5_turbo_0125,0.5795841063698206 +yi_34b_chat,0.5793988997113997 +gemini_1.0_pro,0.5205318491032778 +gpt_3.5_turbo_0613,0.5196837944664031 +llama3_8b_instruct,0.5166348882210227 +yi_1.5_9b_chat,0.5150335775335776 +qwen2_7b_instruct,0.4803418803418803 +phi_3_mini_128k_instruct,0.47774531890678346 +mixtral_8x7b_instruct_v0.1,0.47245816635618004 +starling_lm_7b_beta,0.46037960638800973 +qwen1.5_14b_chat,0.45760855624301 +tulu_2_dpo_70b,0.44326821637746006 +llama3.1_8b_instruct,0.4429972804972805 +command_r,0.42476786498525626 +openhermes_2.5_mistral_7b,0.4133219954648526 +mistral_7b_instruct_v0.2,0.38528271156947624 +yi_1.5_6b_chat,0.3616155902920609 +llama_2_70b_chat,0.3429423284465301 +starling_lm_7b_alpha,0.3192125334982478 +llama3_8b,0.3191327255539897 +gemma_1.1_7b_it,0.3093664233370116 +zephyr_7b_beta,0.3012633624878523 +qwen1.5_7b,0.29290520556048505 +gemma_7b,0.29047416067876425 +vicuna_33b_v1.3,0.28480038480038483 +qwen1.5_7b_chat,0.27333417049803604 +llama_2_13b,0.2660179289106947 +mistral_7b_instruct_v0.3,0.21805555555555559 +yi_6b_chat,0.20091647770219198 +yi_6b,0.19687349577512162 +qwen1.5_4b,0.16834733893557421 +vicuna_7b_v1.5,0.14973544973544975 +gemma_7b_it,0.14039115646258504 +qwen1.5_4b_chat,0.14036924293526934 +phi_2,0.1326664119754182 +llama_2_7b_chat,0.11841995751468631 +gemma_1.1_2b_it,0.09431689342403628 +llama_2_7b,0.06859327581964463 +qwen1.5_1.8b_chat,0.06363517629273932 +gemma_2b,0.05727290916366547 +olmo_7b,0.011775543550753635 +qwen1.5_0.5b_chat,0.008163265306122448 diff --git a/cache/agreements_cache_7b814a45375ad6b75add8b396f69c2cd.csv b/cache/agreements_cache_7b814a45375ad6b75add8b396f69c2cd.csv new file mode 100644 index 0000000000000000000000000000000000000000..62d507ea17f6a0fd017e605c469b9bedf36b3336 --- /dev/null +++ b/cache/agreements_cache_7b814a45375ad6b75add8b396f69c2cd.csv @@ -0,0 +1,1781 @@ +scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.3333333333333333,0.21637345679012346 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,-0.1111111111111111,0.7274895282186948 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.1111111111111111,0.7274895282186948 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,-0.1111111111111111,0.7274895282186948 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,-0.28888888888888886,0.2912483465608466 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.24444444444444444,0.38071979717813054 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.5555555555555555,0.02860945767195767 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,-0.37777777777777777,0.1557418430335097 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.022222222222222223,1.0 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.1111111111111111,0.7274895282186948 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,-0.1111111111111111,0.7274895282186948 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,-0.06666666666666667,0.8618005952380953 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.19999999999999998,0.4843127204585538 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,-0.1111111111111111,0.7274895282186948 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.5111111111111111,0.04662257495590829 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,-0.4222222222222222,0.10831349206349207 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.022222222222222223,1.0 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.3333333333333333,0.21637345679012346 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.37777777777777777,0.1557418430335097 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.28888888888888886,0.2912483465608466 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.28888888888888886,0.2912483465608466 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.022222222222222223,1.0 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.5555555555555555,0.02860945767195767 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.6,0.016666115520282188 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,-0.06666666666666667,0.8618005952380953 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.19999999999999998,0.4843127204585538 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.8989331499509894,0.0003280163150135276 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.8090398349558905,0.0012254240706707103 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.6440611887195306,0.01102341638822145 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.40451991747794525,0.1059975484249457 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.6440611887195306,0.01102341638822145 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.6,0.016666115520282188 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.5111111111111111,0.04662257495590829 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.24444444444444444,0.38071979717813054 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.5555555555555555,0.02860945767195767 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.5111111111111111,0.04662257495590829 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.24444444444444444,0.38071979717813054 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.06666666666666667,0.8618005952380953 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.4222222222222222,0.10831349206349207 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.4222222222222222,0.10831349206349207 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.3333333333333333,0.21637345679012346 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.3333333333333333,0.21637345679012346 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.24444444444444444,0.38071979717813054 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.4222222222222222,0.10831349206349207 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.022222222222222223,1.0 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.6444444444444444,0.009148478835978836 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,-0.15555555555555553,0.6006536596119929 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.3333333333333333,0.21637345679012346 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.7191465199607915,0.004057136032371292 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.8090398349558905,0.0012254240706707103 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.8539864924534399,0.0006436975254696865 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.8989331499509894,0.0003280163150135276 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.5111111111111111,0.04662257495590829 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.9438798074485389,0.0001621317520439264 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.8090398349558905,0.0012254240706707103 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.49441323247304414,0.048193488293190756 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.5111111111111111,0.04662257495590829 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.6,0.016666115520282188 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.49441323247304414,0.048193488293190756 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.28888888888888886,0.2912483465608466 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.022222222222222223,1.0 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.5393598899705937,0.03114121059579671 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.4666666666666666,0.07255015432098766 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.6741998624632421,0.0070583320485280866 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.8539864924534399,0.0006436975254696865 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.6137949055234262,0.01491204965521593 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.7640931774583409,0.002263469812035174 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.522862326927363,0.03809415806109578 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.8989331499509894,0.0003280163150135276 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.6741998624632421,0.0070583320485280866 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.5111111111111111,0.04662257495590829 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.5393598899705937,0.03114121059579671 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.5843065474681431,0.019550269092885535 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.7191465199607915,0.004057136032371292 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.5843065474681431,0.019550269092885535 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.15555555555555553,0.6006536596119929 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.37777777777777777,0.1557418430335097 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.6,0.016666115520282188 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.37777777777777777,0.1557418430335097 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.4222222222222222,0.10831349206349207 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.19999999999999998,0.4843127204585538 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.5555555555555555,0.02860945767195767 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.5555555555555555,0.02860945767195767 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.4666666666666666,0.07255015432098766 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.7777777777777777,0.0009463183421516755 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.6,0.016666115520282188 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,-0.08989331499509894,0.7194375444233914 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.34099716973523675,0.17621399555130546 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.4600437062282361,0.06941907499936387 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.26967994498529685,0.2811980995641792 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.5111111111111111,0.04662257495590829 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.4222222222222222,0.10831349206349207 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.4222222222222222,0.10831349206349207 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.5843065474681431,0.019550269092885535 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.5111111111111111,0.04662257495590829 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.4222222222222222,0.10831349206349207 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.19999999999999998,0.4843127204585538 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.28888888888888886,0.2912483465608466 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.6,0.016666115520282188 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.3333333333333333,0.21637345679012346 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.4222222222222222,0.10831349206349207 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.5111111111111111,0.04662257495590829 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.37777777777777777,0.1557418430335097 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.37777777777777777,0.1557418430335097 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.6,0.016666115520282188 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.37777777777777777,0.1557418430335097 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.5843065474681431,0.019550269092885535 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.8539864924534399,0.0006436975254696865 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.7191465199607915,0.004057136032371292 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.6741998624632421,0.0070583320485280866 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.5843065474681431,0.019550269092885535 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.6137949055234262,0.01491204965521593 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.6741998624632421,0.0070583320485280866 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.5555555555555555,0.02860945767195767 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.40451991747794525,0.1059975484249457 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.5393598899705937,0.03114121059579671 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.5683286162253945,0.02418521832271127 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.5843065474681431,0.019550269092885535 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.4666666666666666,0.07255015432098766 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.6,0.016666115520282188 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.6,0.016666115520282188 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.6444444444444444,0.009148478835978836 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,1,0.8539864924534399,0.0006436975254696865 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,9,0.7191465199607915,0.004057136032371292 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,4,0.7777777777777777,0.0009463183421516755 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.4222222222222222,0.10831349206349207 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.6,0.016666115520282188 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.6,0.016666115520282188 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.4222222222222222,0.10831349206349207 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.7777777777777777,0.0009463183421516755 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.8539864924534399,0.0006436975254696865 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.8222222222222221,0.0003576940035273369 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.40451991747794525,0.1059975484249457 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.49441323247304414,0.048193488293190756 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.49441323247304414,0.048193488293190756 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.40451991747794525,0.1059975484249457 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.5843065474681431,0.019550269092885535 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.8989331499509894,0.0003280163150135276 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.5555555555555555,0.02860945767195767 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.4666666666666666,0.07255015432098766 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.5111111111111111,0.04662257495590829 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.7191465199607915,0.004057136032371292 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.6741998624632421,0.0070583320485280866 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.5683286162253945,0.02418521832271127 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.8090398349558905,0.0012254240706707103 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.37777777777777777,0.1557418430335097 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.7191465199607915,0.004057136032371292 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.28888888888888886,0.2912483465608466 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.8090398349558905,0.0012254240706707103 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.5393598899705937,0.03114121059579671 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.4666666666666666,0.07255015432098766 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.40451991747794525,0.1059975484249457 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.6,0.016666115520282188 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.5111111111111111,0.04662257495590829 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.24444444444444444,0.38071979717813054 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.1111111111111111,0.7274895282186948 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.28888888888888886,0.2912483465608466 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.4222222222222222,0.10831349206349207 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.28888888888888886,0.2912483465608466 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.06666666666666667,0.8618005952380953 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.1111111111111111,0.7274895282186948 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.3333333333333333,0.21637345679012346 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.06666666666666667,0.8618005952380953 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.5111111111111111,0.04662257495590829 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.5111111111111111,0.04662257495590829 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.5111111111111111,0.04662257495590829 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.5555555555555555,0.02860945767195767 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.5111111111111111,0.04662257495590829 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.4222222222222222,0.10831349206349207 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.3333333333333333,0.21637345679012346 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.4666666666666666,0.07255015432098766 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.3333333333333333,0.21637345679012346 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.37777777777777777,0.1557418430335097 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.37777777777777777,0.1557418430335097 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.7191465199607915,0.004057136032371292 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.7191465199607915,0.004057136032371292 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.6292532049656926,0.011921001496914019 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.5555555555555555,0.02860945767195767 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.4222222222222222,0.10831349206349207 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.6,0.016666115520282188 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.5555555555555555,0.02860945767195767 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.5555555555555555,0.02860945767195767 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.5111111111111111,0.04662257495590829 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.4666666666666666,0.07255015432098766 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.37777777777777777,0.1557418430335097 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.4222222222222222,0.10831349206349207 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.28888888888888886,0.2912483465608466 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.4666666666666666,0.07255015432098766 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.4666666666666666,0.07255015432098766 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.6,0.016666115520282188 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.4666666666666666,0.07255015432098766 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.4666666666666666,0.07255015432098766 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.06666666666666667,0.8618005952380953 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,0,0.26967994498529685,0.2811980995641792 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,1,0.35957325998039574,0.15076277502664528 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,2,0.49441323247304414,0.048193488293190756 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,3,0.5393598899705937,0.03114121059579671 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,4,0.22473328748774735,0.36917141633269157 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,5,0.3146266024828463,0.2086677876982641 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,6,0.28888888888888886,0.2912483465608466 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,7,0.5393598899705937,0.03114121059579671 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,8,0.26967994498529685,0.2811980995641792 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,9,0.3146266024828463,0.2086677876982641 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.9438798074485389,0.0001621317520439264 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.8090398349558905,0.0012254240706707103 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9320589306096472,0.00021829510003985143 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.9320589306096472,0.00021829510003985143 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8539864924534399,0.0006436975254696865 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7640931774583409,0.002263469812035174 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.9438798074485389,0.0001621317520439264 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.9555555555555554,5.5114638447971785e-06 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.6444444444444444,0.009148478835978836 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.6444444444444444,0.009148478835978836 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.5555555555555555,0.02860945767195767 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.6444444444444444,0.009148478835978836 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.5555555555555555,0.02860945767195767 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.6444444444444444,0.009148478835978836 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.6,0.016666115520282188 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.6444444444444444,0.009148478835978836 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.5555555555555555,0.02860945767195767 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.6,0.016666115520282188 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.5555555555555555,0.02860945767195767 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.6888888888888888,0.00468694885361552 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.8222222222222221,0.0003576940035273369 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.7777777777777777,0.0009463183421516755 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.8989331499509894,0.0003280163150135276 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.8989331499509894,0.0003280163150135276 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.5111111111111111,0.04662257495590829 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.7777777777777777,0.0009463183421516755 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.28888888888888886,0.2912483465608466 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.06666666666666667,0.8618005952380953 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.5111111111111111,0.04662257495590829 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.4666666666666666,0.07255015432098766 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.4222222222222222,0.10831349206349207 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.35957325998039574,0.15076277502664528 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.4666666666666666,0.07255015432098766 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.5111111111111111,0.04662257495590829 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.37777777777777777,0.1557418430335097 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.6444444444444444,0.009148478835978836 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.49441323247304414,0.048193488293190756 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.5111111111111111,0.04662257495590829 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.15555555555555553,0.6006536596119929 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.6292532049656926,0.011921001496914019 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.4666666666666666,0.07255015432098766 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.5111111111111111,0.04662257495590829 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.26967994498529685,0.2811980995641792 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.4222222222222222,0.10831349206349207 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.5111111111111111,0.04662257495590829 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.6741998624632421,0.0070583320485280866 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.7501937734175208,0.0029250200956793346 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6292532049656926,0.011921001496914019 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.5520524474738833,0.029345108174841844 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.37777777777777777,0.1557418430335097 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.7640931774583409,0.002263469812035174 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.7191465199607915,0.004057136032371292 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.6292532049656926,0.011921001496914019 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.5111111111111111,0.04662257495590829 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.4222222222222222,0.10831349206349207 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.5111111111111111,0.04662257495590829 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7191465199607915,0.004057136032371292 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.8090398349558905,0.0012254240706707103 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.6292532049656926,0.011921001496914019 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.4666666666666666,0.07255015432098766 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.5111111111111111,0.04662257495590829 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.6888888888888888,0.00468694885361552 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.5843065474681431,0.019550269092885535 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.24444444444444444,0.38071979717813054 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6,0.016666115520282188 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.3146266024828463,0.2086677876982641 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7501937734175208,0.0029250200956793346 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.5111111111111111,0.04662257495590829 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.6,0.016666115520282188 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.35957325998039574,0.15076277502664528 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.6741998624632421,0.0070583320485280866 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.7191465199607915,0.004057136032371292 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.6741998624632421,0.0070583320485280866 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.37777777777777777,0.1557418430335097 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.5111111111111111,0.04662257495590829 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.49441323247304414,0.048193488293190756 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.6444444444444444,0.009148478835978836 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.5393598899705937,0.03114121059579671 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.7640931774583409,0.002263469812035174 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.7047274841194893,0.005187148855929351 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.9438798074485389,0.0001621317520439264 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.9888264649460883,7.772240795323086e-05 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.8090398349558905,0.0012254240706707103 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.7191465199607915,0.004057136032371292 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.7047274841194893,0.005187148855929351 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.9888264649460883,7.772240795323086e-05 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.7047274841194893,0.005187148855929351 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.9438798074485389,0.0001621317520439264 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.8989331499509894,0.0003280163150135276 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.8539864924534399,0.0006436975254696865 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.8989331499509894,0.0003280163150135276 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.6,0.016666115520282188 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.5393598899705937,0.03114121059579671 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.6444444444444444,0.009148478835978836 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.7777777777777777,0.0009463183421516755 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.7333333333333333,0.002212852733686067 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.26967994498529685,0.2811980995641792 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.1111111111111111,0.7274895282186948 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.4494665749754947,0.07248608508684644 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.5555555555555555,0.02860945767195767 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.7640931774583409,0.002263469812035174 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.8989331499509894,0.0003280163150135276 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.5555555555555555,0.02860945767195767 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.8222222222222221,0.0003576940035273369 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,0,0.9438798074485389,0.0001621317520439264 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,1,0.9775252199076787,0.00010567442661664933 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,4,0.8865926413116155,0.000437257592706733 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,5,0.9438798074485389,0.0001621317520439264 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,8,0.8539864924534399,0.0006436975254696865 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.5111111111111111,0.04662257495590829 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7333333333333333,0.002212852733686067 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,0,0.3333333333333333,0.21637345679012346 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,1,-0.1111111111111111,0.7274895282186948 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,2,0.1111111111111111,0.7274895282186948 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,3,-0.1111111111111111,0.7274895282186948 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,4,-0.28888888888888886,0.2912483465608466 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,5,0.24444444444444444,0.38071979717813054 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,7,-0.37777777777777777,0.1557418430335097 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,8,0.022222222222222223,1.0 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,9,0.6,0.016666115520282188 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,0,0.1111111111111111,0.7274895282186948 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,1,-0.1111111111111111,0.7274895282186948 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,2,-0.06666666666666667,0.8618005952380953 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,3,0.19999999999999998,0.4843127204585538 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,4,-0.1111111111111111,0.7274895282186948 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,7,-0.4222222222222222,0.10831349206349207 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,8,0.022222222222222223,1.0 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,0,0.3333333333333333,0.21637345679012346 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,1,0.37777777777777777,0.1557418430335097 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,2,0.28888888888888886,0.2912483465608466 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,3,0.28888888888888886,0.2912483465608466 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,4,0.022222222222222223,1.0 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,5,0.5555555555555555,0.02860945767195767 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,6,0.6,0.016666115520282188 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,7,-0.06666666666666667,0.8618005952380953 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,8,0.19999999999999998,0.4843127204585538 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,1,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,2,0.8090398349558905,0.0012254240706707103 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,4,0.6440611887195306,0.01102341638822145 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,7,0.40451991747794525,0.1059975484249457 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,8,0.6440611887195306,0.01102341638822145 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,0,0.6,0.016666115520282188 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,4,0.24444444444444444,0.38071979717813054 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,5,0.5555555555555555,0.02860945767195767 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,6,0.5111111111111111,0.04662257495590829 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,7,0.24444444444444444,0.38071979717813054 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,8,0.06666666666666667,0.8618005952380953 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,4,0.4222222222222222,0.10831349206349207 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,7,0.4222222222222222,0.10831349206349207 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,0,0.3333333333333333,0.21637345679012346 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,1,0.3333333333333333,0.21637345679012346 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,2,0.24444444444444444,0.38071979717813054 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,3,0.4222222222222222,0.10831349206349207 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,4,0.022222222222222223,1.0 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,7,-0.15555555555555553,0.6006536596119929 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,8,0.3333333333333333,0.21637345679012346 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,9,0.7191465199607915,0.004057136032371292 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,0,0.8090398349558905,0.0012254240706707103 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,1,0.8539864924534399,0.0006436975254696865 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,3,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,5,0.9438798074485389,0.0001621317520439264 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,6,0.8090398349558905,0.0012254240706707103 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,7,0.49441323247304414,0.048193488293190756 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,0,0.5111111111111111,0.04662257495590829 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,1,0.6,0.016666115520282188 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,2,0.49441323247304414,0.048193488293190756 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,4,0.28888888888888886,0.2912483465608466 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,7,0.022222222222222223,1.0 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,8,0.5393598899705937,0.03114121059579671 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.4666666666666666,0.07255015432098766 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.6741998624632421,0.0070583320485280866 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.8539864924534399,0.0006436975254696865 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.6137949055234262,0.01491204965521593 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.7640931774583409,0.002263469812035174 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.522862326927363,0.03809415806109578 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.6741998624632421,0.0070583320485280866 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.5393598899705937,0.03114121059579671 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.5843065474681431,0.019550269092885535 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.7191465199607915,0.004057136032371292 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.5843065474681431,0.019550269092885535 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.6,0.016666115520282188 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.15555555555555553,0.6006536596119929 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.37777777777777777,0.1557418430335097 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.6,0.016666115520282188 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.37777777777777777,0.1557418430335097 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.4222222222222222,0.10831349206349207 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.19999999999999998,0.4843127204585538 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.5555555555555555,0.02860945767195767 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.4666666666666666,0.07255015432098766 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.6,0.016666115520282188 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,1,-0.08989331499509894,0.7194375444233914 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.34099716973523675,0.17621399555130546 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.4600437062282361,0.06941907499936387 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.26967994498529685,0.2811980995641792 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.4222222222222222,0.10831349206349207 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.4222222222222222,0.10831349206349207 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.5843065474681431,0.019550269092885535 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.4222222222222222,0.10831349206349207 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.19999999999999998,0.4843127204585538 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.28888888888888886,0.2912483465608466 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.6,0.016666115520282188 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.6,0.016666115520282188 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.3333333333333333,0.21637345679012346 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,0,0.4222222222222222,0.10831349206349207 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,1,0.5111111111111111,0.04662257495590829 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,4,0.37777777777777777,0.1557418430335097 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,5,0.37777777777777777,0.1557418430335097 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,6,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,8,0.37777777777777777,0.1557418430335097 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,1,0.5843065474681431,0.019550269092885535 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,2,0.8539864924534399,0.0006436975254696865 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,6,0.7191465199607915,0.004057136032371292 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,7,0.6741998624632421,0.0070583320485280866 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,8,0.5843065474681431,0.019550269092885535 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,1,0.6137949055234262,0.01491204965521593 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,2,0.6741998624632421,0.0070583320485280866 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,3,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,4,0.40451991747794525,0.1059975484249457 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,5,0.5393598899705937,0.03114121059579671 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,6,0.5683286162253945,0.02418521832271127 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,7,0.5843065474681431,0.019550269092885535 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,8,0.4666666666666666,0.07255015432098766 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,9,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,1,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,5,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,1,0.8539864924534399,0.0006436975254696865 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,9,0.7191465199607915,0.004057136032371292 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,4,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,0,0.4222222222222222,0.10831349206349207 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,2,0.6,0.016666115520282188 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,2,0.6,0.016666115520282188 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,0,0.4222222222222222,0.10831349206349207 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,4,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,5,0.8539864924534399,0.0006436975254696865 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,8,0.40451991747794525,0.1059975484249457 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,1,0.49441323247304414,0.048193488293190756 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,2,0.49441323247304414,0.048193488293190756 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,3,0.40451991747794525,0.1059975484249457 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,4,0.5843065474681431,0.019550269092885535 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,5,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,7,0.5555555555555555,0.02860945767195767 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,0,0.4666666666666666,0.07255015432098766 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,4,0.7191465199607915,0.004057136032371292 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,5,0.6741998624632421,0.0070583320485280866 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,6,0.5683286162253945,0.02418521832271127 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,9,0.8090398349558905,0.0012254240706707103 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,1,0.37777777777777777,0.1557418430335097 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,0,0.7191465199607915,0.004057136032371292 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,1,0.28888888888888886,0.2912483465608466 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,4,0.8090398349558905,0.0012254240706707103 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,5,0.5393598899705937,0.03114121059579671 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,9,0.4666666666666666,0.07255015432098766 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,0,0.40451991747794525,0.1059975484249457 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,2,0.6,0.016666115520282188 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,0,0.24444444444444444,0.38071979717813054 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,1,0.1111111111111111,0.7274895282186948 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,2,0.28888888888888886,0.2912483465608466 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,3,0.4222222222222222,0.10831349206349207 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,4,0.28888888888888886,0.2912483465608466 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,5,0.06666666666666667,0.8618005952380953 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,6,0.1111111111111111,0.7274895282186948 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,7,0.3333333333333333,0.21637345679012346 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,8,0.06666666666666667,0.8618005952380953 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,1,0.5111111111111111,0.04662257495590829 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,8,0.5111111111111111,0.04662257495590829 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,0,0.4222222222222222,0.10831349206349207 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,1,0.3333333333333333,0.21637345679012346 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,4,0.4666666666666666,0.07255015432098766 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,5,0.3333333333333333,0.21637345679012346 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,6,0.37777777777777777,0.1557418430335097 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,8,0.37777777777777777,0.1557418430335097 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,3,0.7191465199607915,0.004057136032371292 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,5,0.7191465199607915,0.004057136032371292 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,6,0.6292532049656926,0.011921001496914019 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,1,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,3,0.4222222222222222,0.10831349206349207 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,5,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,8,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,9,0.5111111111111111,0.04662257495590829 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,0,0.4666666666666666,0.07255015432098766 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,1,0.37777777777777777,0.1557418430335097 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,2,0.4222222222222222,0.10831349206349207 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,3,0.28888888888888886,0.2912483465608466 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,4,0.4666666666666666,0.07255015432098766 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,5,0.4666666666666666,0.07255015432098766 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,6,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,7,0.4666666666666666,0.07255015432098766 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,8,0.4666666666666666,0.07255015432098766 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,9,0.06666666666666667,0.8618005952380953 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,0,0.26967994498529685,0.2811980995641792 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,1,0.35957325998039574,0.15076277502664528 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,2,0.49441323247304414,0.048193488293190756 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,3,0.5393598899705937,0.03114121059579671 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,4,0.22473328748774735,0.36917141633269157 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,5,0.3146266024828463,0.2086677876982641 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,6,0.28888888888888886,0.2912483465608466 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,7,0.5393598899705937,0.03114121059579671 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,8,0.26967994498529685,0.2811980995641792 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,9,0.3146266024828463,0.2086677876982641 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,0,0.9438798074485389,0.0001621317520439264 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,4,0.8090398349558905,0.0012254240706707103 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,6,0.9320589306096472,0.00021829510003985143 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,7,0.9320589306096472,0.00021829510003985143 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,8,0.8539864924534399,0.0006436975254696865 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,9,0.7640931774583409,0.002263469812035174 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,0,0.9438798074485389,0.0001621317520439264 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,8,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,4,0.5555555555555555,0.02860945767195767 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,4,0.5555555555555555,0.02860945767195767 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,0,0.6,0.016666115520282188 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,8,0.5555555555555555,0.02860945767195767 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,0,0.6,0.016666115520282188 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,4,0.5555555555555555,0.02860945767195767 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.6,0.016666115520282188 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.28888888888888886,0.2912483465608466 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.06666666666666667,0.8618005952380953 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.4666666666666666,0.07255015432098766 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.4222222222222222,0.10831349206349207 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.35957325998039574,0.15076277502664528 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.4666666666666666,0.07255015432098766 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.37777777777777777,0.1557418430335097 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.49441323247304414,0.048193488293190756 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.15555555555555553,0.6006536596119929 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.6292532049656926,0.011921001496914019 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.4666666666666666,0.07255015432098766 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.26967994498529685,0.2811980995641792 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.4222222222222222,0.10831349206349207 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,2,0.5111111111111111,0.04662257495590829 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,5,0.6741998624632421,0.0070583320485280866 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,7,0.7501937734175208,0.0029250200956793346 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,9,0.6292532049656926,0.011921001496914019 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,1,0.5520524474738833,0.029345108174841844 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,2,0.37777777777777777,0.1557418430335097 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,4,0.7640931774583409,0.002263469812035174 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,6,0.7191465199607915,0.004057136032371292 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,7,0.6292532049656926,0.011921001496914019 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,8,0.5111111111111111,0.04662257495590829 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,1,0.4222222222222222,0.10831349206349207 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,2,0.5111111111111111,0.04662257495590829 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,3,0.7191465199607915,0.004057136032371292 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,5,0.8090398349558905,0.0012254240706707103 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,7,0.6292532049656926,0.011921001496914019 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,8,0.4666666666666666,0.07255015432098766 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,2,0.5111111111111111,0.04662257495590829 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,7,0.5843065474681431,0.019550269092885535 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,8,0.6,0.016666115520282188 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,9,0.6,0.016666115520282188 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,0,0.24444444444444444,0.38071979717813054 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,1,0.6,0.016666115520282188 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,2,0.3146266024828463,0.2086677876982641 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,3,0.7501937734175208,0.0029250200956793346 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,6,0.6,0.016666115520282188 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,7,0.35957325998039574,0.15076277502664528 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,8,0.6,0.016666115520282188 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,3,0.6741998624632421,0.0070583320485280866 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,5,0.7191465199607915,0.004057136032371292 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,6,0.6741998624632421,0.0070583320485280866 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,8,0.37777777777777777,0.1557418430335097 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,9,0.5111111111111111,0.04662257495590829 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,2,0.49441323247304414,0.048193488293190756 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,8,0.6,0.016666115520282188 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,9,0.6,0.016666115520282188 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,4,0.5393598899705937,0.03114121059579671 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,5,0.7640931774583409,0.002263469812035174 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,0,0.7047274841194893,0.005187148855929351 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,1,0.9438798074485389,0.0001621317520439264 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,2,0.9888264649460883,7.772240795323086e-05 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,3,0.8090398349558905,0.0012254240706707103 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,4,0.7191465199607915,0.004057136032371292 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,5,0.7047274841194893,0.005187148855929351 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,6,0.9888264649460883,7.772240795323086e-05 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,7,0.7047274841194893,0.005187148855929351 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,8,0.9438798074485389,0.0001621317520439264 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,0,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,2,0.8539864924534399,0.0006436975254696865 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,0,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,1,0.6,0.016666115520282188 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,2,0.5393598899705937,0.03114121059579671 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,8,0.6,0.016666115520282188 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,3,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,4,0.26967994498529685,0.2811980995641792 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,7,0.1111111111111111,0.7274895282186948 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,8,0.4494665749754947,0.07248608508684644 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.5555555555555555,0.02860945767195767 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,0,0.7640931774583409,0.002263469812035174 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,1,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,1,0.5555555555555555,0.02860945767195767 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,0,0.9438798074485389,0.0001621317520439264 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,1,0.9775252199076787,0.00010567442661664933 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,4,0.8865926413116155,0.000437257592706733 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,5,0.9438798074485389,0.0001621317520439264 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,8,0.8539864924534399,0.0006436975254696865 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,3,0.7333333333333333,0.002212852733686067 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,8,0.6,0.016666115520282188 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 diff --git a/cache/agreements_cache_9aca1000dd25da3a044f5fd80fad0266.csv b/cache/agreements_cache_9aca1000dd25da3a044f5fd80fad0266.csv deleted file mode 100644 index d68c9f200fc86eab696c2c727d751acf4d1edf82..0000000000000000000000000000000000000000 --- a/cache/agreements_cache_9aca1000dd25da3a044f5fd80fad0266.csv +++ /dev/null @@ -1,901 +0,0 @@ -scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value -grounding,biggen_240612,aggregate,holistic,kendall,random,5,0,0.7378647873726218,0.07697417298126676 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,0,0.7378647873726218,0.07697417298126676 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,4,0.7378647873726218,0.07697417298126676 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -planning,biggen_240612,aggregate,holistic,kendall,random,5,0,-0.19999999999999998,0.8166666666666667 -planning,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -planning,biggen_240612,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -planning,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -planning,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -planning,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -planning,biggen_240612,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -planning,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -planning,biggen_240612,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -planning,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,0,0.19999999999999998,0.8166666666666667 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -safety,biggen_240612,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -safety,biggen_240612,aggregate,holistic,kendall,random,5,1,0.0,1.0 -safety,biggen_240612,aggregate,holistic,kendall,random,5,2,-0.39999999999999997,0.48333333333333334 -safety,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -safety,biggen_240612,aggregate,holistic,kendall,random,5,4,-0.7999999999999999,0.08333333333333333 -safety,biggen_240612,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -safety,biggen_240612,aggregate,holistic,kendall,random,5,6,-0.19999999999999998,0.8166666666666667 -safety,biggen_240612,aggregate,holistic,kendall,random,5,7,-0.39999999999999997,0.48333333333333334 -safety,biggen_240612,aggregate,holistic,kendall,random,5,8,-0.19999999999999998,0.8166666666666667 -safety,biggen_240612,aggregate,holistic,kendall,random,5,9,0.0,1.0 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,0,0.0,1.0 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.10540925533894598,0.8005421074231263 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.10540925533894598,0.8005421074231263 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.10540925533894598,0.8005421074231263 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,8,-0.5270462766947298,0.206507295485425 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,9,-0.39999999999999997,0.48333333333333334 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.19999999999999998,0.8166666666666667 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.19999999999999998,0.8166666666666667 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7378647873726218,0.07697417298126676 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7378647873726218,0.07697417298126676 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.5270462766947298,0.206507295485425 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.5270462766947298,0.206507295485425 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7378647873726218,0.07697417298126676 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.5270462766947298,0.206507295485425 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.31622776601683794,0.44848886103153174 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,0,-0.39999999999999997,0.48333333333333334 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.19999999999999998,0.8166666666666667 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,2,-0.19999999999999998,0.8166666666666667 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,3,-0.6,0.23333333333333334 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.19999999999999998,0.8166666666666667 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.0,1.0 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.19999999999999998,0.8166666666666667 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9486832980505137,0.02297740150320607 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9486832980505137,0.02297740150320607 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.0,1.0 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9486832980505137,0.02297740150320607 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.19999999999999998,0.8166666666666667 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9486832980505137,0.02297740150320607 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9486832980505137,0.02297740150320607 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.5270462766947298,0.206507295485425 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,0,0.7378647873726218,0.07697417298126676 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,2,0.6,0.23333333333333334 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,5,0.7378647873726218,0.07697417298126676 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,0,0.7378647873726218,0.07697417298126676 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,2,0.19999999999999998,0.8166666666666667 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,4,0.7378647873726218,0.07697417298126676 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,5,0.7378647873726218,0.07697417298126676 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,planning,biggen_240612,kendall,random,5,0,-0.19999999999999998,0.8166666666666667 -aggregate,holistic,planning,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,planning,biggen_240612,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,planning,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,planning,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -aggregate,holistic,planning,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,planning,biggen_240612,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,planning,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,planning,biggen_240612,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -aggregate,holistic,planning,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,2,0.6,0.23333333333333334 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,4,0.6,0.23333333333333334 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,7,0.6,0.23333333333333334 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,9,0.6,0.23333333333333334 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,0,0.19999999999999998,0.8166666666666667 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,safety,biggen_240612,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -aggregate,holistic,safety,biggen_240612,kendall,random,5,1,0.0,1.0 -aggregate,holistic,safety,biggen_240612,kendall,random,5,2,-0.39999999999999997,0.48333333333333334 -aggregate,holistic,safety,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,safety,biggen_240612,kendall,random,5,4,-0.7999999999999999,0.08333333333333333 -aggregate,holistic,safety,biggen_240612,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -aggregate,holistic,safety,biggen_240612,kendall,random,5,6,-0.19999999999999998,0.8166666666666667 -aggregate,holistic,safety,biggen_240612,kendall,random,5,7,-0.39999999999999997,0.48333333333333334 -aggregate,holistic,safety,biggen_240612,kendall,random,5,8,-0.19999999999999998,0.8166666666666667 -aggregate,holistic,safety,biggen_240612,kendall,random,5,9,0.0,1.0 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,1,0.6,0.23333333333333334 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,4,0.19999999999999998,0.8166666666666667 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,0,0.0,1.0 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,7,0.6,0.23333333333333334 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,1,0.39999999999999997,0.48333333333333334 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,3,0.39999999999999997,0.48333333333333334 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,6,0.39999999999999997,0.48333333333333334 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,3,0.39999999999999997,0.48333333333333334 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,8,0.6,0.23333333333333334 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,1,0.39999999999999997,0.48333333333333334 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,3,0.10540925533894598,0.8005421074231263 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,4,0.19999999999999998,0.8166666666666667 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,6,0.10540925533894598,0.8005421074231263 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,7,0.10540925533894598,0.8005421074231263 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,8,-0.5270462766947298,0.206507295485425 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,9,-0.39999999999999997,0.48333333333333334 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,9,0.6,0.23333333333333334 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,9,0.6,0.23333333333333334 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,1,0.6,0.23333333333333334 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,2,0.19999999999999998,0.8166666666666667 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,3,0.19999999999999998,0.8166666666666667 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,9,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,1,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,7,0.19999999999999998,0.8166666666666667 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,9,0.39999999999999997,0.48333333333333334 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,3,0.39999999999999997,0.48333333333333334 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,0,0.7378647873726218,0.07697417298126676 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,2,0.7378647873726218,0.07697417298126676 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,3,0.5270462766947298,0.206507295485425 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,0,0.5270462766947298,0.206507295485425 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,1,0.7378647873726218,0.07697417298126676 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,2,0.5270462766947298,0.206507295485425 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,3,0.31622776601683794,0.44848886103153174 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,5,0.7378647873726218,0.07697417298126676 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,1,0.6,0.23333333333333334 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,7,0.6,0.23333333333333334 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,9,0.6,0.23333333333333334 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,0,-0.39999999999999997,0.48333333333333334 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,1,0.19999999999999998,0.8166666666666667 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,2,-0.19999999999999998,0.8166666666666667 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,3,-0.6,0.23333333333333334 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,4,0.19999999999999998,0.8166666666666667 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,5,0.19999999999999998,0.8166666666666667 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,6,0.0,1.0 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,8,0.19999999999999998,0.8166666666666667 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,9,0.6,0.23333333333333334 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,1,0.6,0.23333333333333334 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,9,0.6,0.23333333333333334 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,0,0.9486832980505137,0.02297740150320607 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,3,0.9486832980505137,0.02297740150320607 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,4,0.6,0.23333333333333334 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,6,0.0,1.0 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,0,0.9486832980505137,0.02297740150320607 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,7,0.19999999999999998,0.8166666666666667 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,8,0.6,0.23333333333333334 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,1,0.9486832980505137,0.02297740150320607 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,4,0.9486832980505137,0.02297740150320607 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,8,0.5270462766947298,0.206507295485425 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333 diff --git a/cache/agreements_cache_b002484b092f2f62850354386e68e83e.csv b/cache/agreements_cache_b002484b092f2f62850354386e68e83e.csv deleted file mode 100644 index 796e08d8e42cd842adcce2b772b777bfb7b20ae1..0000000000000000000000000000000000000000 --- a/cache/agreements_cache_b002484b092f2f62850354386e68e83e.csv +++ /dev/null @@ -1,921 +0,0 @@ -scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value -grounding,biggen_240612,aggregate,holistic,kendall,random,5,0,0.7378647873726218,0.07697417298126676 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -grounding,biggen_240612,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,0,0.7378647873726218,0.07697417298126676 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,4,0.7378647873726218,0.07697417298126676 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -instruction_following,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -planning,biggen_240612,aggregate,holistic,kendall,random,5,0,-0.19999999999999998,0.8166666666666667 -planning,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -planning,biggen_240612,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -planning,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -planning,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -planning,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -planning,biggen_240612,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -planning,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -planning,biggen_240612,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -planning,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -reasoning,biggen_240612,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,0,0.19999999999999998,0.8166666666666667 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -refinement,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -safety,biggen_240612,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -safety,biggen_240612,aggregate,holistic,kendall,random,5,1,0.0,1.0 -safety,biggen_240612,aggregate,holistic,kendall,random,5,2,-0.39999999999999997,0.48333333333333334 -safety,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -safety,biggen_240612,aggregate,holistic,kendall,random,5,4,-0.7999999999999999,0.08333333333333333 -safety,biggen_240612,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -safety,biggen_240612,aggregate,holistic,kendall,random,5,6,-0.19999999999999998,0.8166666666666667 -safety,biggen_240612,aggregate,holistic,kendall,random,5,7,-0.39999999999999997,0.48333333333333334 -safety,biggen_240612,aggregate,holistic,kendall,random,5,8,-0.19999999999999998,0.8166666666666667 -safety,biggen_240612,aggregate,holistic,kendall,random,5,9,0.0,1.0 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -theory_of_mind,biggen_240612,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,0,0.0,1.0 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -tool_usage,biggen_240612,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.39999999999999997,0.48333333333333334 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -hellaswag,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334 -humaneval,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.10540925533894598,0.8005421074231263 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.10540925533894598,0.8005421074231263 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.10540925533894598,0.8005421074231263 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,8,-0.5270462766947298,0.206507295485425 -mbpp,BLZ_240312,aggregate,holistic,kendall,random,5,9,-0.39999999999999997,0.48333333333333334 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -winogrande,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -mixeval_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -arena_elo_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -triviaqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -mmlu_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -drop_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -hellaswag_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -commonsenseqa_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -triviaqa_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.19999999999999998,0.8166666666666667 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.19999999999999998,0.8166666666666667 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -mmlu_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.39999999999999997,0.48333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.19999999999999998,0.8166666666666667 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -drop_hard_mixed,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.39999999999999997,0.48333333333333334 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334 -livebench_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7378647873726218,0.07697417298126676 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7378647873726218,0.07697417298126676 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.5270462766947298,0.206507295485425 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -reasoning_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.5270462766947298,0.206507295485425 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7378647873726218,0.07697417298126676 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.5270462766947298,0.206507295485425 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.31622776601683794,0.44848886103153174 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7378647873726218,0.07697417298126676 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334 -coding_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334 -mathematics_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -data_analysis_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -language_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,0,-0.39999999999999997,0.48333333333333334 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,1,0.19999999999999998,0.8166666666666667 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,2,-0.19999999999999998,0.8166666666666667 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,3,-0.6,0.23333333333333334 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,4,0.19999999999999998,0.8166666666666667 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,5,0.19999999999999998,0.8166666666666667 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,6,0.0,1.0 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,8,0.19999999999999998,0.8166666666666667 -if_average,livebench_240701,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334 -mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,2,0.6,0.23333333333333334 -mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,3,0.39999999999999997,0.48333333333333334 -mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334 -mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334 -mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -arena_hard,arena_hard_2404,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -agieval,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9486832980505137,0.02297740150320607 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -arc_c,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9486832980505137,0.02297740150320607 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -alpacav1,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.6,0.23333333333333334 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.0,1.0 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -alpacav2,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -alpacaeval2_lc,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9486832980505137,0.02297740150320607 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -arena_elo,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.6,0.23333333333333334 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -bbh,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -eq_benchv2,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -gpt4all,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.19999999999999998,0.8166666666666667 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.6,0.23333333333333334 -hugging_6,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9486832980505137,0.02297740150320607 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9486832980505137,0.02297740150320607 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.6,0.23333333333333334 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.5270462766947298,0.206507295485425 -llmonitor,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.6,0.23333333333333334 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.6,0.23333333333333334 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -magi,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.6,0.23333333333333334 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.9999999999999999,0.016666666666666666 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.6,0.23333333333333334 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.6,0.23333333333333334 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -mmlu,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -mt_bench,BLZ_240312,aggregate,holistic,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -mixeval,mixeval_240601,aggregate,holistic,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,0,0.7378647873726218,0.07697417298126676 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,2,0.6,0.23333333333333334 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,5,0.7378647873726218,0.07697417298126676 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,grounding,biggen_240612,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,0,0.7378647873726218,0.07697417298126676 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,2,0.19999999999999998,0.8166666666666667 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,4,0.7378647873726218,0.07697417298126676 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,5,0.7378647873726218,0.07697417298126676 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,instruction_following,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,planning,biggen_240612,kendall,random,5,0,-0.19999999999999998,0.8166666666666667 -aggregate,holistic,planning,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,planning,biggen_240612,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,planning,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,planning,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -aggregate,holistic,planning,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,planning,biggen_240612,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,planning,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,planning,biggen_240612,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -aggregate,holistic,planning,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,2,0.6,0.23333333333333334 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,4,0.6,0.23333333333333334 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,7,0.6,0.23333333333333334 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning,biggen_240612,kendall,random,5,9,0.6,0.23333333333333334 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,0,0.19999999999999998,0.8166666666666667 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,refinement,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,safety,biggen_240612,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -aggregate,holistic,safety,biggen_240612,kendall,random,5,1,0.0,1.0 -aggregate,holistic,safety,biggen_240612,kendall,random,5,2,-0.39999999999999997,0.48333333333333334 -aggregate,holistic,safety,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,safety,biggen_240612,kendall,random,5,4,-0.7999999999999999,0.08333333333333333 -aggregate,holistic,safety,biggen_240612,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -aggregate,holistic,safety,biggen_240612,kendall,random,5,6,-0.19999999999999998,0.8166666666666667 -aggregate,holistic,safety,biggen_240612,kendall,random,5,7,-0.39999999999999997,0.48333333333333334 -aggregate,holistic,safety,biggen_240612,kendall,random,5,8,-0.19999999999999998,0.8166666666666667 -aggregate,holistic,safety,biggen_240612,kendall,random,5,9,0.0,1.0 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,1,0.6,0.23333333333333334 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,4,0.19999999999999998,0.8166666666666667 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,theory_of_mind,biggen_240612,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,0,0.0,1.0 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,7,0.6,0.23333333333333334 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,tool_usage,biggen_240612,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,1,0.39999999999999997,0.48333333333333334 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,3,0.39999999999999997,0.48333333333333334 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,6,0.39999999999999997,0.48333333333333334 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,hellaswag,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,3,0.39999999999999997,0.48333333333333334 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,8,0.6,0.23333333333333334 -aggregate,holistic,humaneval,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,1,0.39999999999999997,0.48333333333333334 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,2,0.6,0.23333333333333334 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,3,0.10540925533894598,0.8005421074231263 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,4,0.19999999999999998,0.8166666666666667 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,6,0.10540925533894598,0.8005421074231263 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,7,0.10540925533894598,0.8005421074231263 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,8,-0.5270462766947298,0.206507295485425 -aggregate,holistic,mbpp,BLZ_240312,kendall,random,5,9,-0.39999999999999997,0.48333333333333334 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,winogrande,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval_hard_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_mixed,mixeval_240601,kendall,random,5,9,0.6,0.23333333333333334 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -aggregate,holistic,hellaswag_mixed,mixeval_240601,kendall,random,5,9,0.6,0.23333333333333334 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,commonsenseqa_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,triviaqa_hard_mixed,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,1,0.6,0.23333333333333334 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,2,0.19999999999999998,0.8166666666666667 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,3,0.19999999999999998,0.8166666666666667 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu_hard_mixed,mixeval_240601,kendall,random,5,9,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,1,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,4,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,7,0.19999999999999998,0.8166666666666667 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -aggregate,holistic,drop_hard_mixed,mixeval_240601,kendall,random,5,9,0.39999999999999997,0.48333333333333334 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,3,0.39999999999999997,0.48333333333333334 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334 -aggregate,holistic,livebench_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,0,0.7378647873726218,0.07697417298126676 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,2,0.7378647873726218,0.07697417298126676 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,3,0.5270462766947298,0.206507295485425 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,reasoning_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,0,0.5270462766947298,0.206507295485425 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,1,0.7378647873726218,0.07697417298126676 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,2,0.5270462766947298,0.206507295485425 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,3,0.31622776601683794,0.44848886103153174 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,5,0.7378647873726218,0.07697417298126676 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334 -aggregate,holistic,coding_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,4,0.6,0.23333333333333334 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,8,0.6,0.23333333333333334 -aggregate,holistic,mathematics_average,livebench_240701,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,data_analysis_average,livebench_240701,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,1,0.6,0.23333333333333334 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,2,0.6,0.23333333333333334 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,7,0.6,0.23333333333333334 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,language_average,livebench_240701,kendall,random,5,9,0.6,0.23333333333333334 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,0,-0.39999999999999997,0.48333333333333334 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,1,0.19999999999999998,0.8166666666666667 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,2,-0.19999999999999998,0.8166666666666667 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,3,-0.6,0.23333333333333334 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,4,0.19999999999999998,0.8166666666666667 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,5,0.19999999999999998,0.8166666666666667 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,6,0.0,1.0 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,8,0.19999999999999998,0.8166666666666667 -aggregate,holistic,if_average,livebench_240701,kendall,random,5,9,0.6,0.23333333333333334 -aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,2,0.6,0.23333333333333334 -aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,3,0.39999999999999997,0.48333333333333334 -aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,4,0.6,0.23333333333333334 -aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,8,0.6,0.23333333333333334 -aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,0,0.39999999999999997,0.48333333333333334 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,1,0.6,0.23333333333333334 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arena_hard,arena_hard_2404,kendall,random,5,9,0.6,0.23333333333333334 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,agieval,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,0,0.9486832980505137,0.02297740150320607 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arc_c,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,3,0.9486832980505137,0.02297740150320607 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav1,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,4,0.6,0.23333333333333334 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,6,0.0,1.0 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,alpacav2,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,alpacaeval2_lc,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,0,0.9486832980505137,0.02297740150320607 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,7,0.39999999999999997,0.48333333333333334 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,arena_elo,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,0,0.6,0.23333333333333334 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,bbh,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,eq_benchv2,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -aggregate,holistic,gpt4all,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,7,0.19999999999999998,0.8166666666666667 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,8,0.6,0.23333333333333334 -aggregate,holistic,hugging_6,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,0,0.9999999999999999,0.016666666666666666 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,1,0.9486832980505137,0.02297740150320607 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,4,0.9486832980505137,0.02297740150320607 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,5,0.7999999999999999,0.08333333333333333 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,6,0.6,0.23333333333333334 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,7,0.9999999999999999,0.016666666666666666 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,8,0.5270462766947298,0.206507295485425 -aggregate,holistic,llmonitor,BLZ_240312,kendall,random,5,9,0.7999999999999999,0.08333333333333333 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,1,0.6,0.23333333333333334 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,2,0.39999999999999997,0.48333333333333334 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,3,0.6,0.23333333333333334 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,8,0.39999999999999997,0.48333333333333334 -aggregate,holistic,magi,BLZ_240312,kendall,random,5,9,0.6,0.23333333333333334 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,2,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,5,0.6,0.23333333333333334 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,7,0.6,0.23333333333333334 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,8,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mmlu,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,1,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,3,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,4,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,5,0.39999999999999997,0.48333333333333334 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,6,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mt_bench,BLZ_240312,kendall,random,5,9,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,0,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,1,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,2,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,3,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,4,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,5,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,6,0.9999999999999999,0.016666666666666666 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,7,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,8,0.7999999999999999,0.08333333333333333 -aggregate,holistic,mixeval,mixeval_240601,kendall,random,5,9,0.7999999999999999,0.08333333333333333 diff --git a/cache/agreements_cache_bdd8d629730630ed8e73cb56f53f335b.csv b/cache/agreements_cache_bdd8d629730630ed8e73cb56f53f335b.csv new file mode 100644 index 0000000000000000000000000000000000000000..a70800b2515cdba057965b2d4ed1e9005e91c7cc --- /dev/null +++ b/cache/agreements_cache_bdd8d629730630ed8e73cb56f53f335b.csv @@ -0,0 +1,1801 @@ +scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.3333333333333333,0.21637345679012346 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,-0.1111111111111111,0.7274895282186948 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.1111111111111111,0.7274895282186948 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,-0.1111111111111111,0.7274895282186948 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,-0.28888888888888886,0.2912483465608466 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.24444444444444444,0.38071979717813054 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.5555555555555555,0.02860945767195767 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,-0.37777777777777777,0.1557418430335097 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.022222222222222223,1.0 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.1111111111111111,0.7274895282186948 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,-0.1111111111111111,0.7274895282186948 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,-0.06666666666666667,0.8618005952380953 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.19999999999999998,0.4843127204585538 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,-0.1111111111111111,0.7274895282186948 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.5111111111111111,0.04662257495590829 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,-0.4222222222222222,0.10831349206349207 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.022222222222222223,1.0 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.3333333333333333,0.21637345679012346 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.37777777777777777,0.1557418430335097 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.28888888888888886,0.2912483465608466 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.28888888888888886,0.2912483465608466 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.022222222222222223,1.0 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.5555555555555555,0.02860945767195767 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.6,0.016666115520282188 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,-0.06666666666666667,0.8618005952380953 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.19999999999999998,0.4843127204585538 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.8989331499509894,0.0003280163150135276 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.8090398349558905,0.0012254240706707103 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.6440611887195306,0.01102341638822145 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.40451991747794525,0.1059975484249457 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.6440611887195306,0.01102341638822145 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.6,0.016666115520282188 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.5111111111111111,0.04662257495590829 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.24444444444444444,0.38071979717813054 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.5555555555555555,0.02860945767195767 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.5111111111111111,0.04662257495590829 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.24444444444444444,0.38071979717813054 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.06666666666666667,0.8618005952380953 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.4222222222222222,0.10831349206349207 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.4222222222222222,0.10831349206349207 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.3333333333333333,0.21637345679012346 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.3333333333333333,0.21637345679012346 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.24444444444444444,0.38071979717813054 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.4222222222222222,0.10831349206349207 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.022222222222222223,1.0 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.6444444444444444,0.009148478835978836 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,-0.15555555555555553,0.6006536596119929 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.3333333333333333,0.21637345679012346 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.7191465199607915,0.004057136032371292 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.8090398349558905,0.0012254240706707103 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.8539864924534399,0.0006436975254696865 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.8989331499509894,0.0003280163150135276 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.5111111111111111,0.04662257495590829 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.9438798074485389,0.0001621317520439264 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.8090398349558905,0.0012254240706707103 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.49441323247304414,0.048193488293190756 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.5111111111111111,0.04662257495590829 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.6,0.016666115520282188 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.49441323247304414,0.048193488293190756 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.28888888888888886,0.2912483465608466 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.022222222222222223,1.0 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.5393598899705937,0.03114121059579671 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.4666666666666666,0.07255015432098766 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.6741998624632421,0.0070583320485280866 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.8539864924534399,0.0006436975254696865 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.6137949055234262,0.01491204965521593 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.7640931774583409,0.002263469812035174 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.522862326927363,0.03809415806109578 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +HFv2 BBH Raw,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.8989331499509894,0.0003280163150135276 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.6741998624632421,0.0070583320485280866 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.5111111111111111,0.04662257495590829 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.5393598899705937,0.03114121059579671 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.5843065474681431,0.019550269092885535 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.7191465199607915,0.004057136032371292 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.5843065474681431,0.019550269092885535 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.15555555555555553,0.6006536596119929 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.37777777777777777,0.1557418430335097 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.6,0.016666115520282188 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.37777777777777777,0.1557418430335097 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.4222222222222222,0.10831349206349207 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.19999999999999998,0.4843127204585538 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.5555555555555555,0.02860945767195767 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.5555555555555555,0.02860945767195767 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.4666666666666666,0.07255015432098766 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.7777777777777777,0.0009463183421516755 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.6,0.016666115520282188 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,-0.08989331499509894,0.7194375444233914 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.34099716973523675,0.17621399555130546 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.4600437062282361,0.06941907499936387 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.26967994498529685,0.2811980995641792 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.5111111111111111,0.04662257495590829 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.4222222222222222,0.10831349206349207 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.4222222222222222,0.10831349206349207 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.5843065474681431,0.019550269092885535 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.5111111111111111,0.04662257495590829 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.4222222222222222,0.10831349206349207 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.19999999999999998,0.4843127204585538 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.28888888888888886,0.2912483465608466 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.6,0.016666115520282188 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.3333333333333333,0.21637345679012346 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.4222222222222222,0.10831349206349207 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.5111111111111111,0.04662257495590829 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.37777777777777777,0.1557418430335097 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.37777777777777777,0.1557418430335097 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.6,0.016666115520282188 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.37777777777777777,0.1557418430335097 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.5843065474681431,0.019550269092885535 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.8539864924534399,0.0006436975254696865 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.7191465199607915,0.004057136032371292 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.6741998624632421,0.0070583320485280866 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.5843065474681431,0.019550269092885535 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.6137949055234262,0.01491204965521593 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.6741998624632421,0.0070583320485280866 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.5555555555555555,0.02860945767195767 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.40451991747794525,0.1059975484249457 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.5393598899705937,0.03114121059579671 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.5683286162253945,0.02418521832271127 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.5843065474681431,0.019550269092885535 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.4666666666666666,0.07255015432098766 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.6,0.016666115520282188 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.6,0.016666115520282188 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.6444444444444444,0.009148478835978836 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,1,0.8539864924534399,0.0006436975254696865 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +Helm MMLU,helm_mmlu_240829.csv,aggregate,holistic,kendall,random,10,9,0.7191465199607915,0.004057136032371292 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,4,0.7777777777777777,0.0009463183421516755 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +MMLU Pro,mmlu_pro_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.4222222222222222,0.10831349206349207 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.6,0.016666115520282188 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +MixEval TriviaQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.6,0.016666115520282188 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +MixEval MMLU,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.4222222222222222,0.10831349206349207 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.7777777777777777,0.0009463183421516755 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.8539864924534399,0.0006436975254696865 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.8222222222222221,0.0003576940035273369 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.40451991747794525,0.1059975484249457 +MixEval DROP,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.49441323247304414,0.048193488293190756 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.49441323247304414,0.048193488293190756 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.40451991747794525,0.1059975484249457 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.5843065474681431,0.019550269092885535 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.8989331499509894,0.0003280163150135276 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.5555555555555555,0.02860945767195767 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +MixEval HellaSwag,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.4666666666666666,0.07255015432098766 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.5111111111111111,0.04662257495590829 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.7191465199607915,0.004057136032371292 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.6741998624632421,0.0070583320485280866 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.5683286162253945,0.02418521832271127 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.8090398349558905,0.0012254240706707103 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.37777777777777777,0.1557418430335097 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.7191465199607915,0.004057136032371292 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.28888888888888886,0.2912483465608466 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.8090398349558905,0.0012254240706707103 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.5393598899705937,0.03114121059579671 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.4666666666666666,0.07255015432098766 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.40451991747794525,0.1059975484249457 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.6,0.016666115520282188 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.5111111111111111,0.04662257495590829 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +MixEval DROP Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.24444444444444444,0.38071979717813054 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.1111111111111111,0.7274895282186948 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.28888888888888886,0.2912483465608466 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.4222222222222222,0.10831349206349207 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.28888888888888886,0.2912483465608466 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.06666666666666667,0.8618005952380953 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.1111111111111111,0.7274895282186948 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.3333333333333333,0.21637345679012346 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.06666666666666667,0.8618005952380953 +OpenCompass Language,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.5111111111111111,0.04662257495590829 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.5111111111111111,0.04662257495590829 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.5111111111111111,0.04662257495590829 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.5555555555555555,0.02860945767195767 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.5111111111111111,0.04662257495590829 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.4222222222222222,0.10831349206349207 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.3333333333333333,0.21637345679012346 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.4666666666666666,0.07255015432098766 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.3333333333333333,0.21637345679012346 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.37777777777777777,0.1557418430335097 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.37777777777777777,0.1557418430335097 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +OpenCompass Math,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.7191465199607915,0.004057136032371292 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.7191465199607915,0.004057136032371292 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.6292532049656926,0.011921001496914019 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +OpenCompass Code,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.5555555555555555,0.02860945767195767 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.4222222222222222,0.10831349206349207 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.6,0.016666115520282188 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.5555555555555555,0.02860945767195767 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.5555555555555555,0.02860945767195767 +OpenCompass Instruction,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.5111111111111111,0.04662257495590829 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.4666666666666666,0.07255015432098766 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.37777777777777777,0.1557418430335097 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.4222222222222222,0.10831349206349207 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.28888888888888886,0.2912483465608466 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.4666666666666666,0.07255015432098766 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.4666666666666666,0.07255015432098766 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.6,0.016666115520282188 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.4666666666666666,0.07255015432098766 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.4666666666666666,0.07255015432098766 +OpenCompass Agent,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.06666666666666667,0.8618005952380953 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,0,0.26967994498529685,0.2811980995641792 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,1,0.35957325998039574,0.15076277502664528 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,2,0.49441323247304414,0.048193488293190756 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,3,0.5393598899705937,0.03114121059579671 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,4,0.22473328748774735,0.36917141633269157 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,5,0.3146266024828463,0.2086677876982641 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,6,0.28888888888888886,0.2912483465608466 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,7,0.5393598899705937,0.03114121059579671 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,8,0.26967994498529685,0.2811980995641792 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,holistic,kendall,random,10,9,0.3146266024828463,0.2086677876982641 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.9438798074485389,0.0001621317520439264 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.8090398349558905,0.0012254240706707103 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9320589306096472,0.00021829510003985143 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.9320589306096472,0.00021829510003985143 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8539864924534399,0.0006436975254696865 +LiveBench Reasoning,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7640931774583409,0.002263469812035174 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.9438798074485389,0.0001621317520439264 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05 +LiveBench Coding,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.9555555555555554,5.5114638447971785e-06 +LiveBench Mathematics,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.6444444444444444,0.009148478835978836 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.6444444444444444,0.009148478835978836 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +LiveBench Data Analysis,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.5555555555555555,0.02860945767195767 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +LiveBench Language,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.6444444444444444,0.009148478835978836 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.5555555555555555,0.02860945767195767 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.6444444444444444,0.009148478835978836 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +LiveBench Instruction Following,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.6,0.016666115520282188 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.6444444444444444,0.009148478835978836 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.5555555555555555,0.02860945767195767 +WildBench Information Seeking,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.6,0.016666115520282188 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.5555555555555555,0.02860945767195767 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.6888888888888888,0.00468694885361552 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +WildBench Creative,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +WildBench Code Debugging,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.8222222222222221,0.0003576940035273369 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +WildBench Math & Data,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.7777777777777777,0.0009463183421516755 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +WildBench Score,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.8989331499509894,0.0003280163150135276 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.8989331499509894,0.0003280163150135276 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.5111111111111111,0.04662257495590829 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.7777777777777777,0.0009463183421516755 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.28888888888888886,0.2912483465608466 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.06666666666666667,0.8618005952380953 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.5111111111111111,0.04662257495590829 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.4666666666666666,0.07255015432098766 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.4222222222222222,0.10831349206349207 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.35957325998039574,0.15076277502664528 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.4666666666666666,0.07255015432098766 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.5111111111111111,0.04662257495590829 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.37777777777777777,0.1557418430335097 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.6444444444444444,0.009148478835978836 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.49441323247304414,0.048193488293190756 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.5111111111111111,0.04662257495590829 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.15555555555555553,0.6006536596119929 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.6292532049656926,0.011921001496914019 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.4666666666666666,0.07255015432098766 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.5111111111111111,0.04662257495590829 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.26967994498529685,0.2811980995641792 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.4222222222222222,0.10831349206349207 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.5111111111111111,0.04662257495590829 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.6741998624632421,0.0070583320485280866 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.7501937734175208,0.0029250200956793346 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +BigBench Grounding,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6292532049656926,0.011921001496914019 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.5520524474738833,0.029345108174841844 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.37777777777777777,0.1557418430335097 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.7640931774583409,0.002263469812035174 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.7191465199607915,0.004057136032371292 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.6292532049656926,0.011921001496914019 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.5111111111111111,0.04662257495590829 +BigBench Instruction Following,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.4222222222222222,0.10831349206349207 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.5111111111111111,0.04662257495590829 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7191465199607915,0.004057136032371292 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.8090398349558905,0.0012254240706707103 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.6292532049656926,0.011921001496914019 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.4666666666666666,0.07255015432098766 +BigBench Planning,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +BigBench Reasoning,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.5111111111111111,0.04662257495590829 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.6888888888888888,0.00468694885361552 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.5843065474681431,0.019550269092885535 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188 +BigBench Refinement,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.24444444444444444,0.38071979717813054 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6,0.016666115520282188 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.3146266024828463,0.2086677876982641 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7501937734175208,0.0029250200956793346 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.5111111111111111,0.04662257495590829 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.6,0.016666115520282188 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.35957325998039574,0.15076277502664528 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188 +BigBench Safety,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.6741998624632421,0.0070583320485280866 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.7191465199607915,0.004057136032371292 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.6741998624632421,0.0070583320485280866 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.37777777777777777,0.1557418430335097 +BigBench Theory of Mind,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.5111111111111111,0.04662257495590829 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.49441323247304414,0.048193488293190756 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.6444444444444444,0.009148478835978836 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188 +BigBench Tool Usage,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6,0.016666115520282188 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.5393598899705937,0.03114121059579671 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.7640931774583409,0.002263469812035174 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +BigBench Multilingual,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.7047274841194893,0.005187148855929351 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.9438798074485389,0.0001621317520439264 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.9888264649460883,7.772240795323086e-05 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.8090398349558905,0.0012254240706707103 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.7191465199607915,0.004057136032371292 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.7047274841194893,0.005187148855929351 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.9888264649460883,7.772240795323086e-05 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.7047274841194893,0.005187148855929351 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.9438798074485389,0.0001621317520439264 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.8989331499509894,0.0003280163150135276 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.8539864924534399,0.0006436975254696865 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.6,0.016666115520282188 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +LiveBench Coding Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.8989331499509894,0.0003280163150135276 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.6,0.016666115520282188 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.5393598899705937,0.03114121059579671 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.6444444444444444,0.009148478835978836 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +LiveBench Language Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,10,7,0.4222222222222222,0.10831349206349207 +mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +mybench_average,Uploaded Benchmark,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,1,0.7777777777777777,0.0009463183421516755 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,3,0.7333333333333333,0.002212852733686067 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,4,0.26967994498529685,0.2811980995641792 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,7,0.1111111111111111,0.7274895282186948 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,8,0.4494665749754947,0.07248608508684644 +Helm Lite,helm_lite_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,4,0.6,0.016666115520282188 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,7,0.5555555555555555,0.02860945767195767 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,holistic,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07 +Arena Elo,chatbot_arena_240829.csv,aggregate,holistic,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.7640931774583409,0.002263469812035174 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.8989331499509894,0.0003280163150135276 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +MixEval,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,1,0.5555555555555555,0.02860945767195767 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05 +MixEval Hard,mixeval_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,7,0.8222222222222221,0.0003576940035273369 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05 +OpenCompass,opencompass_240829.csv,aggregate,holistic,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,0,0.9438798074485389,0.0001621317520439264 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,1,0.9775252199076787,0.00010567442661664933 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,4,0.8865926413116155,0.000437257592706733 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,5,0.9438798074485389,0.0001621317520439264 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,8,0.8539864924534399,0.0006436975254696865 +AlphacaEval v2lc,alphacaeval_v2lc.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +LiveBench 240725,livebench_240829.csv,aggregate,holistic,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +WildBench Elo LC,wildbench_240829.csv,aggregate,holistic,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07 +Arena Hard,arena_hard_240829.csv,aggregate,holistic,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,4,0.5111111111111111,0.04662257495590829 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,holistic,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,3,0.7333333333333333,0.002212852733686067 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,8,0.6,0.016666115520282188 +BigBench,biggen_240829.csv,aggregate,holistic,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +LiveBench 240624,livebench_240701.csv,aggregate,holistic,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,0,0.3333333333333333,0.21637345679012346 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,1,-0.1111111111111111,0.7274895282186948 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,2,0.1111111111111111,0.7274895282186948 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,3,-0.1111111111111111,0.7274895282186948 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,4,-0.28888888888888886,0.2912483465608466 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,5,0.24444444444444444,0.38071979717813054 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,7,-0.37777777777777777,0.1557418430335097 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,8,0.022222222222222223,1.0 +aggregate,holistic,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,10,9,0.6,0.016666115520282188 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,0,0.1111111111111111,0.7274895282186948 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,1,-0.1111111111111111,0.7274895282186948 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,2,-0.06666666666666667,0.8618005952380953 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,3,0.19999999999999998,0.4843127204585538 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,4,-0.1111111111111111,0.7274895282186948 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,7,-0.4222222222222222,0.10831349206349207 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,8,0.022222222222222223,1.0 +aggregate,holistic,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,0,0.3333333333333333,0.21637345679012346 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,1,0.37777777777777777,0.1557418430335097 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,2,0.28888888888888886,0.2912483465608466 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,3,0.28888888888888886,0.2912483465608466 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,4,0.022222222222222223,1.0 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,5,0.5555555555555555,0.02860945767195767 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,6,0.6,0.016666115520282188 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,7,-0.06666666666666667,0.8618005952380953 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,8,0.19999999999999998,0.4843127204585538 +aggregate,holistic,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,1,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,2,0.8090398349558905,0.0012254240706707103 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,4,0.6440611887195306,0.01102341638822145 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,7,0.40451991747794525,0.1059975484249457 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,8,0.6440611887195306,0.01102341638822145 +aggregate,holistic,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,0,0.6,0.016666115520282188 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,4,0.24444444444444444,0.38071979717813054 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,5,0.5555555555555555,0.02860945767195767 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,6,0.5111111111111111,0.04662257495590829 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,7,0.24444444444444444,0.38071979717813054 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,8,0.06666666666666667,0.8618005952380953 +aggregate,holistic,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,4,0.4222222222222222,0.10831349206349207 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,7,0.4222222222222222,0.10831349206349207 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,0,0.3333333333333333,0.21637345679012346 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,1,0.3333333333333333,0.21637345679012346 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,2,0.24444444444444444,0.38071979717813054 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,3,0.4222222222222222,0.10831349206349207 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,4,0.022222222222222223,1.0 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,7,-0.15555555555555553,0.6006536596119929 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,8,0.3333333333333333,0.21637345679012346 +aggregate,holistic,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,10,9,0.7191465199607915,0.004057136032371292 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,0,0.8090398349558905,0.0012254240706707103 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,1,0.8539864924534399,0.0006436975254696865 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,3,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,5,0.9438798074485389,0.0001621317520439264 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,6,0.8090398349558905,0.0012254240706707103 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,7,0.49441323247304414,0.048193488293190756 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,0,0.5111111111111111,0.04662257495590829 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,1,0.6,0.016666115520282188 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,2,0.49441323247304414,0.048193488293190756 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,4,0.28888888888888886,0.2912483465608466 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,7,0.022222222222222223,1.0 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,8,0.5393598899705937,0.03114121059579671 +aggregate,holistic,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.4666666666666666,0.07255015432098766 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.6741998624632421,0.0070583320485280866 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.8539864924534399,0.0006436975254696865 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.6137949055234262,0.01491204965521593 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.7640931774583409,0.002263469812035174 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.522862326927363,0.03809415806109578 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv2 BBH Raw,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.6741998624632421,0.0070583320485280866 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.5393598899705937,0.03114121059579671 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.5843065474681431,0.019550269092885535 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.7191465199607915,0.004057136032371292 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.5843065474681431,0.019550269092885535 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +aggregate,holistic,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.6,0.016666115520282188 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.15555555555555553,0.6006536596119929 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.37777777777777777,0.1557418430335097 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.6,0.016666115520282188 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.37777777777777777,0.1557418430335097 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.4222222222222222,0.10831349206349207 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.19999999999999998,0.4843127204585538 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.5555555555555555,0.02860945767195767 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.4666666666666666,0.07255015432098766 +aggregate,holistic,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.6,0.016666115520282188 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,1,-0.08989331499509894,0.7194375444233914 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.34099716973523675,0.17621399555130546 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.4600437062282361,0.06941907499936387 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.26967994498529685,0.2811980995641792 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.4222222222222222,0.10831349206349207 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.4222222222222222,0.10831349206349207 +aggregate,holistic,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.5843065474681431,0.019550269092885535 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.4222222222222222,0.10831349206349207 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.19999999999999998,0.4843127204585538 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.28888888888888886,0.2912483465608466 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.6,0.016666115520282188 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.6,0.016666115520282188 +aggregate,holistic,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.3333333333333333,0.21637345679012346 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,0,0.4222222222222222,0.10831349206349207 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,1,0.5111111111111111,0.04662257495590829 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,4,0.37777777777777777,0.1557418430335097 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,5,0.37777777777777777,0.1557418430335097 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,6,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,8,0.37777777777777777,0.1557418430335097 +aggregate,holistic,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,1,0.5843065474681431,0.019550269092885535 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,2,0.8539864924534399,0.0006436975254696865 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,6,0.7191465199607915,0.004057136032371292 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,7,0.6741998624632421,0.0070583320485280866 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,8,0.5843065474681431,0.019550269092885535 +aggregate,holistic,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,1,0.6137949055234262,0.01491204965521593 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,2,0.6741998624632421,0.0070583320485280866 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,3,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,4,0.40451991747794525,0.1059975484249457 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,5,0.5393598899705937,0.03114121059579671 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,6,0.5683286162253945,0.02418521832271127 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,7,0.5843065474681431,0.019550269092885535 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,8,0.4666666666666666,0.07255015432098766 +aggregate,holistic,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,10,9,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,1,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,5,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,1,0.8539864924534399,0.0006436975254696865 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Helm MMLU,helm_mmlu_240829.csv,kendall,random,10,9,0.7191465199607915,0.004057136032371292 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,4,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MMLU Pro,mmlu_pro_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,0,0.4222222222222222,0.10831349206349207 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,2,0.6,0.016666115520282188 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval TriviaQA,mixeval_240829.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,2,0.6,0.016666115520282188 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval MMLU,mixeval_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,0,0.4222222222222222,0.10831349206349207 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,4,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,5,0.8539864924534399,0.0006436975254696865 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,8,0.40451991747794525,0.1059975484249457 +aggregate,holistic,MixEval DROP,mixeval_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,1,0.49441323247304414,0.048193488293190756 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,2,0.49441323247304414,0.048193488293190756 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,3,0.40451991747794525,0.1059975484249457 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,4,0.5843065474681431,0.019550269092885535 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,5,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,7,0.5555555555555555,0.02860945767195767 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,MixEval HellaSwag,mixeval_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,0,0.4666666666666666,0.07255015432098766 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,4,0.7191465199607915,0.004057136032371292 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,5,0.6741998624632421,0.0070583320485280866 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,6,0.5683286162253945,0.02418521832271127 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +aggregate,holistic,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,10,9,0.8090398349558905,0.0012254240706707103 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,1,0.37777777777777777,0.1557418430335097 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,0,0.7191465199607915,0.004057136032371292 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,1,0.28888888888888886,0.2912483465608466 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,4,0.8090398349558905,0.0012254240706707103 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,5,0.5393598899705937,0.03114121059579671 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,10,9,0.4666666666666666,0.07255015432098766 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,0,0.40451991747794525,0.1059975484249457 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,2,0.6,0.016666115520282188 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval DROP Hard,mixeval_240829.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,0,0.24444444444444444,0.38071979717813054 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,1,0.1111111111111111,0.7274895282186948 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,2,0.28888888888888886,0.2912483465608466 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,3,0.4222222222222222,0.10831349206349207 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,4,0.28888888888888886,0.2912483465608466 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,5,0.06666666666666667,0.8618005952380953 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,6,0.1111111111111111,0.7274895282186948 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,7,0.3333333333333333,0.21637345679012346 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,8,0.06666666666666667,0.8618005952380953 +aggregate,holistic,OpenCompass Language,opencompass_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,1,0.5111111111111111,0.04662257495590829 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,3,0.5111111111111111,0.04662257495590829 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,8,0.5111111111111111,0.04662257495590829 +aggregate,holistic,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,0,0.4222222222222222,0.10831349206349207 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,1,0.3333333333333333,0.21637345679012346 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,4,0.4666666666666666,0.07255015432098766 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,5,0.3333333333333333,0.21637345679012346 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,6,0.37777777777777777,0.1557418430335097 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,8,0.37777777777777777,0.1557418430335097 +aggregate,holistic,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass Math,opencompass_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,3,0.7191465199607915,0.004057136032371292 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,5,0.7191465199607915,0.004057136032371292 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,6,0.6292532049656926,0.011921001496914019 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass Code,opencompass_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,1,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,3,0.4222222222222222,0.10831349206349207 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,5,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,6,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,8,0.5555555555555555,0.02860945767195767 +aggregate,holistic,OpenCompass Instruction,opencompass_240829.csv,kendall,random,10,9,0.5111111111111111,0.04662257495590829 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,0,0.4666666666666666,0.07255015432098766 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,1,0.37777777777777777,0.1557418430335097 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,2,0.4222222222222222,0.10831349206349207 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,3,0.28888888888888886,0.2912483465608466 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,4,0.4666666666666666,0.07255015432098766 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,5,0.4666666666666666,0.07255015432098766 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,6,0.6,0.016666115520282188 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,7,0.4666666666666666,0.07255015432098766 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,8,0.4666666666666666,0.07255015432098766 +aggregate,holistic,OpenCompass Agent,opencompass_240829.csv,kendall,random,10,9,0.06666666666666667,0.8618005952380953 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,0,0.26967994498529685,0.2811980995641792 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,1,0.35957325998039574,0.15076277502664528 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,2,0.49441323247304414,0.048193488293190756 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,3,0.5393598899705937,0.03114121059579671 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,4,0.22473328748774735,0.36917141633269157 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,5,0.3146266024828463,0.2086677876982641 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,6,0.28888888888888886,0.2912483465608466 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,7,0.5393598899705937,0.03114121059579671 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,8,0.26967994498529685,0.2811980995641792 +aggregate,holistic,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,10,9,0.3146266024828463,0.2086677876982641 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,0,0.9438798074485389,0.0001621317520439264 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,4,0.8090398349558905,0.0012254240706707103 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,6,0.9320589306096472,0.00021829510003985143 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,7,0.9320589306096472,0.00021829510003985143 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,8,0.8539864924534399,0.0006436975254696865 +aggregate,holistic,LiveBench Reasoning,livebench_240829.csv,kendall,random,10,9,0.7640931774583409,0.002263469812035174 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,0,0.9438798074485389,0.0001621317520439264 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Coding,livebench_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,8,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench Mathematics,livebench_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Data Analysis,livebench_240829.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,4,0.5555555555555555,0.02860945767195767 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Language,livebench_240829.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,4,0.5555555555555555,0.02860945767195767 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,6,0.6444444444444444,0.009148478835978836 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench Instruction Following,livebench_240829.csv,kendall,random,10,9,0.5555555555555555,0.02860945767195767 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,0,0.6,0.016666115520282188 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,2,0.6888888888888888,0.00468694885361552 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,8,0.5555555555555555,0.02860945767195767 +aggregate,holistic,WildBench Information Seeking,wildbench_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,0,0.6,0.016666115520282188 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,4,0.5555555555555555,0.02860945767195767 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +aggregate,holistic,WildBench Creative,wildbench_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Code Debugging,wildbench_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Math & Data,wildbench_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,2,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Score,wildbench_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.6,0.016666115520282188 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.28888888888888886,0.2912483465608466 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.06666666666666667,0.8618005952380953 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.4666666666666666,0.07255015432098766 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.4222222222222222,0.10831349206349207 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +aggregate,holistic,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.35957325998039574,0.15076277502664528 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.4666666666666666,0.07255015432098766 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.37777777777777777,0.1557418430335097 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.49441323247304414,0.048193488293190756 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.15555555555555553,0.6006536596119929 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.6292532049656926,0.011921001496914019 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.4666666666666666,0.07255015432098766 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.26967994498529685,0.2811980995641792 +aggregate,holistic,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.4222222222222222,0.10831349206349207 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,2,0.5111111111111111,0.04662257495590829 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,3,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,5,0.6741998624632421,0.0070583320485280866 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,7,0.7501937734175208,0.0029250200956793346 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Grounding,biggen_240829.csv,kendall,random,10,9,0.6292532049656926,0.011921001496914019 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,1,0.5520524474738833,0.029345108174841844 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,2,0.37777777777777777,0.1557418430335097 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,4,0.7640931774583409,0.002263469812035174 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,6,0.7191465199607915,0.004057136032371292 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,7,0.6292532049656926,0.011921001496914019 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,8,0.5111111111111111,0.04662257495590829 +aggregate,holistic,BigBench Instruction Following,biggen_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,1,0.4222222222222222,0.10831349206349207 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,2,0.5111111111111111,0.04662257495590829 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,3,0.7191465199607915,0.004057136032371292 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,5,0.8090398349558905,0.0012254240706707103 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,7,0.6292532049656926,0.011921001496914019 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,8,0.4666666666666666,0.07255015432098766 +aggregate,holistic,BigBench Planning,biggen_240829.csv,kendall,random,10,9,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,4,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,8,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Reasoning,biggen_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,0,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,2,0.5111111111111111,0.04662257495590829 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,5,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,6,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,7,0.5843065474681431,0.019550269092885535 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,8,0.6,0.016666115520282188 +aggregate,holistic,BigBench Refinement,biggen_240829.csv,kendall,random,10,9,0.6,0.016666115520282188 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,0,0.24444444444444444,0.38071979717813054 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,1,0.6,0.016666115520282188 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,2,0.3146266024828463,0.2086677876982641 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,3,0.7501937734175208,0.0029250200956793346 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,6,0.6,0.016666115520282188 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,7,0.35957325998039574,0.15076277502664528 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,8,0.6,0.016666115520282188 +aggregate,holistic,BigBench Safety,biggen_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,0,0.5555555555555555,0.02860945767195767 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,3,0.6741998624632421,0.0070583320485280866 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,5,0.7191465199607915,0.004057136032371292 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,6,0.6741998624632421,0.0070583320485280866 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,8,0.37777777777777777,0.1557418430335097 +aggregate,holistic,BigBench Theory of Mind,biggen_240829.csv,kendall,random,10,9,0.5111111111111111,0.04662257495590829 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,2,0.49441323247304414,0.048193488293190756 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,3,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,5,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,8,0.6,0.016666115520282188 +aggregate,holistic,BigBench Tool Usage,biggen_240829.csv,kendall,random,10,9,0.6,0.016666115520282188 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,4,0.5393598899705937,0.03114121059579671 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,5,0.7640931774583409,0.002263469812035174 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +aggregate,holistic,BigBench Multilingual,biggen_240829.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,0,0.7047274841194893,0.005187148855929351 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,1,0.9438798074485389,0.0001621317520439264 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,2,0.9888264649460883,7.772240795323086e-05 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,3,0.8090398349558905,0.0012254240706707103 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,4,0.7191465199607915,0.004057136032371292 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,5,0.7047274841194893,0.005187148855929351 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,6,0.9888264649460883,7.772240795323086e-05 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,7,0.7047274841194893,0.005187148855929351 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,8,0.9438798074485389,0.0001621317520439264 +aggregate,holistic,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,0,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,2,0.8539864924534399,0.0006436975254696865 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,7,0.6,0.016666115520282188 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Coding Average,livebench_240701.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,2,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07 +aggregate,holistic,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,0,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,1,0.6,0.016666115520282188 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,2,0.5393598899705937,0.03114121059579671 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,3,0.6444444444444444,0.009148478835978836 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,8,0.6,0.016666115520282188 +aggregate,holistic,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,8,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench Language Average,livebench_240701.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,1,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,5,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,10,0,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,10,7,0.4222222222222222,0.10831349206349207 +aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,10,8,0.7333333333333333,0.002212852733686067 +aggregate,holistic,mybench_average,Uploaded Benchmark,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,1,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,2,0.6444444444444444,0.009148478835978836 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,3,0.7333333333333333,0.002212852733686067 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,4,0.26967994498529685,0.2811980995641792 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,7,0.1111111111111111,0.7274895282186948 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,8,0.4494665749754947,0.07248608508684644 +aggregate,holistic,Helm Lite,helm_lite_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,2,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,4,0.6,0.016666115520282188 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,7,0.5555555555555555,0.02860945767195767 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,10,9,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,0,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07 +aggregate,holistic,Arena Elo,chatbot_arena_240829.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,0,0.7640931774583409,0.002263469812035174 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,1,0.8989331499509894,0.0003280163150135276 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,6,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,MixEval,mixeval_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,1,0.5555555555555555,0.02860945767195767 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,5,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,7,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,MixEval Hard,mixeval_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,0,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,1,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,7,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,8,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,OpenCompass,opencompass_240829.csv,kendall,random,10,9,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,0,0.9438798074485389,0.0001621317520439264 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,1,0.9775252199076787,0.00010567442661664933 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,2,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,3,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,4,0.8865926413116155,0.000437257592706733 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,5,0.9438798074485389,0.0001621317520439264 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,8,0.8539864924534399,0.0006436975254696865 +aggregate,holistic,AlphacaEval v2lc,alphacaeval_v2lc.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,1,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,4,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,5,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,6,0.9999999999999999,5.511463844797178e-07 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,7,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,8,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench 240725,livebench_240829.csv,kendall,random,10,9,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,3,0.9999999999999999,5.511463844797178e-07 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,4,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,5,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,6,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,7,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,8,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,WildBench Elo LC,wildbench_240829.csv,kendall,random,10,9,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,0,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,1,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,2,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,3,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,4,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,5,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,6,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,7,0.911111111111111,2.9761904761904762e-05 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,8,0.9999999999999999,5.511463844797178e-07 +aggregate,holistic,Arena Hard,arena_hard_240829.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,1,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,2,0.5555555555555555,0.02860945767195767 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,3,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,4,0.5111111111111111,0.04662257495590829 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,6,0.7333333333333333,0.002212852733686067 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,7,0.6444444444444444,0.009148478835978836 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,10,9,0.7333333333333333,0.002212852733686067 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,0,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,1,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,2,0.4666666666666666,0.07255015432098766 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,3,0.7333333333333333,0.002212852733686067 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,4,0.6444444444444444,0.009148478835978836 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,6,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,7,0.6888888888888888,0.00468694885361552 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,8,0.6,0.016666115520282188 +aggregate,holistic,BigBench,biggen_240829.csv,kendall,random,10,9,0.6888888888888888,0.00468694885361552 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,0,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,1,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,2,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,3,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,4,0.8666666666666666,0.00011518959435626102 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,5,0.8222222222222221,0.0003576940035273369 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,6,0.9555555555555554,5.5114638447971785e-06 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,7,0.7333333333333333,0.002212852733686067 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,8,0.7777777777777777,0.0009463183421516755 +aggregate,holistic,LiveBench 240624,livebench_240701.csv,kendall,random,10,9,0.9555555555555554,5.5114638447971785e-06