diff --git a/cache/aggregate_scoress_cache_2916d5df57069c497d825c9f1fac0bd4.csv b/cache/aggregate_scoress_cache_2916d5df57069c497d825c9f1fac0bd4.csv new file mode 100644 index 0000000000000000000000000000000000000000..27961bb61091f83d66744767f6bc01b01978ef5b --- /dev/null +++ b/cache/aggregate_scoress_cache_2916d5df57069c497d825c9f1fac0bd4.csv @@ -0,0 +1,62 @@ +model,score +claude_3_5_sonnet_20240620,1.0 +gpt_4o_2024_05_13,0.9833333333333333 +gpt_4_0125_preview,0.9666666666666667 +gpt_4o_2024_08_06,0.95 +athene_70b,0.9333333333333333 +gpt_4o_mini,0.9166666666666666 +gemini_1_5_pro_api_preview,0.9 +mistral_large_2407,0.8833333333333333 +llama3_1_405b_instruct,0.8666666666666667 +glm_4_0520,0.85 +yi_large,0.8333333333333334 +deepseek_coder_v2,0.8166666666666667 +claude_3_opus_20240229,0.8 +gemma_2_27b_it,0.7833333333333333 +llama3_1_70b_instruct,0.75 +glm_4_0116,0.75 +glm_4_air,0.7333333333333333 +gpt_4_0314,0.7166666666666667 +gemini_1_5_flash_api_preview,0.7 +qwen2_72b_instruct,0.6833333333333333 +claude_3_sonnet_20240229,0.6666666666666666 +llama3_70b_instruct,0.65 +claude_3_haiku_20240307,0.6333333333333333 +gpt_4_0613,0.6166666666666667 +mistral_large_2402,0.6 +mixtral_8x22b_instruct_v0_1,0.5833333333333334 +qwen1_5_72b_chat,0.5666666666666667 +phi_3_medium_4k_instruct,0.55 +command_r_plus,0.5333333333333333 +mistral_medium,0.5166666666666667 +internlm2_5_20b_chat,0.5 +phi_3_small_8k_instruct,0.48333333333333334 +mistral_next,0.4666666666666667 +gpt_3_5_turbo_0613,0.45 +dbrx_instructruct_preview,0.43333333333333335 +internlm2_20b_chat,0.4166666666666667 +claude_2_0,0.4 +mixtral_8x7b_instruct_v0_1,0.38333333333333336 +gpt_3_5_turbo_0125,0.36666666666666664 +yi_34b_chat,0.35 +starling_lm_7b_beta,0.3333333333333333 +claude_2_1,0.31666666666666665 +llama3_1_8b_instruct,0.3 +snorkel_mistral_pairrm_dpo,0.2833333333333333 +llama3_8b_instruct,0.26666666666666666 +gpt_3_5_turbo_1106,0.25 +gpt_3_5_turbo_0301,0.23333333333333334 +gemini_1_0_pro,0.21666666666666667 +snowflake_arctic_instruct,0.2 +command_r,0.18333333333333332 +phi_3_mini_128k_instruct,0.16666666666666666 +tulu_2_dpo_70b,0.15 +starling_lm_7b_alpha,0.13333333333333333 +mistral_7b_instruct,0.11666666666666667 +gemma_1_1_7b_it,0.1 +llama_2_70b_chat,0.08333333333333333 +vicuna_33b_v1_3,0.06666666666666667 +gemma_7b_it,0.05 +llama_2_7b_chat,0.03333333333333333 +gemma_1_1_2b_it,0.016666666666666666 +gemma_2b_it,0.0 diff --git a/cache/aggregate_scoress_cache_e798cd9f99d4c09af5b81734eecc6592.csv b/cache/aggregate_scoress_cache_e798cd9f99d4c09af5b81734eecc6592.csv index a33ea27eac6e6888824655ca0db1c73ad1843f9b..c96cfee927d08c30467bd7037ce76bdecba861c2 100644 --- a/cache/aggregate_scoress_cache_e798cd9f99d4c09af5b81734eecc6592.csv +++ b/cache/aggregate_scoress_cache_e798cd9f99d4c09af5b81734eecc6592.csv @@ -1,13 +1,122 @@ model,score -gpt_4o_2024_05_13,1.0 -qwen2_72b_instruct,0.8437710437710438 -gemma_2_27b_it,0.8225108225108225 -llama3_70b_instruct,0.7288840788840788 -qwen1.5_110b_chat,0.6958874458874459 -command_r_plus,0.5340909090909091 -qwen1.5_72b_chat,0.510909090909091 -llama3_8b_instruct,0.2897065897065897 -mixtral_8x7b_instruct_v0.1,0.27759740259740256 -command_r,0.1515151515151515 -qwen1.5_7b_chat,0.06897546897546898 -llama_2_7b_chat,0.0 +gpt_4o_2024_05_13,0.9847612958226769 +claude_3_5_sonnet_20240620,0.982905982905983 +gpt_4o_2024_08_06,0.9575873827791986 +gpt_4_turbo_2024_04_09,0.9428463693169576 +gpt_4_0125_preview,0.9171132221004344 +mistral_large_2407,0.8868286445012787 +llama3_1_405b_instruct,0.8672150411280846 +yi_large_preview,0.8641553641553642 +hermes_3_llama3_1_70b,0.8626160990712074 +smaug_qwen2_72b_instruct,0.8593911248710011 +claude_3_opus_20240229,0.8573567665639277 +llama3_1_70b_instruct,0.8528408270971201 +athene_70b,0.8493788819875776 +deepseek_coder_v2,0.8444160272804775 +qwen2_72b_instruct,0.8354710666091739 +yi_large,0.8346273291925466 +gpt_4_0613,0.8146763722211293 +llama3_70b_instruct,0.8127546753337573 +llama3_70b,0.8105600539811066 +gemma_2_27b_it,0.8045273029120115 +gpt_4o_mini_2024_07_18,0.8032033326150972 +gemma_2_9b_it_dpo,0.790057915057915 +llama3_instruct_8b_simpo,0.7884068278805121 +phi_3_5_moe_instruct,0.7808307533539731 +qwen1_5_110b_chat,0.776004448721167 +qwen1_5_32b,0.7658569500674763 +yi_1_5_34b_chat,0.7553884711779449 +llama_2_70b,0.7303193882141251 +mixtral_8x22b_instruct_v0_1,0.7256023690940907 +gemma_2_9b_it_simpo,0.7199248120300753 +qwen1_5_32b_chat,0.7149122807017544 +mixtral_8x22b_v0_1,0.7135490753911806 +yi_34b,0.7128879892037787 +internlm2_5_20b_chat,0.6842105263157895 +phi_3_small_128k_instruct,0.66937564499484 +phi_3_medium_4k_instruct,0.6675079642841117 +claude_3_sonnet_20240229,0.653911731916847 +gemma_2_9b_it,0.6422797189051059 +infinity_instruct_3m_0625_llama3_8b,0.6273115220483642 +mistral_v0_1_7b,0.6239316239316239 +phi_3_5_mini_instruct,0.6202270381836945 +mistral_medium,0.6122209165687427 +mistral_large_2402,0.6058211467418628 +claude_instant_1_2,0.6049896049896051 +claude_2_0,0.6020066889632107 +yi_1_5_9b_chat,0.5881787802840435 +qwen1_5_14b,0.5770917678812416 +command_r_plus,0.5761033510394125 +llama_65b,0.5736992052781527 +gpt_3_5_turbo_0613,0.5724018332713985 +qwen1_5_72b_chat,0.5668371367348349 +phi_3_mini_4k_instruct,0.5548245614035088 +deepseek_llm_67b_chat,0.5506756756756757 +claude_3_haiku_20240307,0.549424005945745 +yi_34b_chat,0.5455449728905107 +dbrx_instructruct,0.5344129554655871 +jurassic_2_jumbo_178b,0.532051282051282 +llama3_1_8b_instruct,0.5175232440678665 +claude_2_1,0.5110980545763154 +qwen2_7b_instruct,0.5034227726178191 +mistral_small_2402,0.49924585218702866 +mixtral_8x7b_v0_1,0.49324324324324326 +glm_4_9b_chat,0.46499582289055974 +qwen1_5_14b_chat,0.4621068436857911 +phi_3_small_8k_instruct,0.45481670929241264 +gpt_3_5_turbo_0301,0.4528985507246377 +snorkel_mistral_pairrm_dpo,0.4521151586368978 +gemma_7b,0.4471997300944669 +gpt_3_5_turbo_0125,0.4401920188365201 +llama3_8b,0.43302968960863697 +dbrx_instruct,0.4266409266409266 +llama3_8b_instruct,0.420135922511747 +phi_3_mini_128k_instruct,0.4153205904787544 +llama_2_13b,0.41490478332583597 +jurassic_2_grande_17b,0.39529914529914534 +openhermes_2_5_mistral_7b,0.3832617447168531 +mistral_7b_v0_3,0.3737553342816501 +mixtral_8x7b_instruct_v0_1,0.3713078251895724 +qwen1_5_7b,0.3508771929824561 +yi_1_5_6b_chat,0.3354636591478697 +falcon_40b,0.32812265707002547 +command_r,0.32386140074759 +internlm2_chat_20b,0.32252252252252256 +mistral_7b_v0_2,0.31970128022759603 +luminous_supreme_70b,0.30128205128205127 +starling_lm_7b_alpha,0.29823530624445954 +yi_6b,0.29234143049932526 +mistral_7b_instruct_v0_2,0.28609513981031004 +zephyr_7b_alpha,0.2838442157327606 +zephyr_7b_beta,0.2666234345800909 +gemma_1_1_7b_it,0.26226051061156724 +mistral_7b_instruct_v0_3,0.2537839697282422 +starling_lm_7b_beta,0.25234441602728047 +llama_2_7b,0.2391288049182786 +luminous_extended_30b,0.2329059829059829 +alpaca_7b,0.22072072072072071 +vicuna_33b_v1_3,0.2056404230317274 +phi_2,0.20087901666849037 +qwen2_1_5b_instruct,0.19711042311661506 +yi_6b_chat,0.1938854489164087 +qwen1_5_7b_chat,0.1916569245052217 +tulu_2_dpo_70b,0.17624223602484473 +qwen1_5_4b_chat,0.1674406604747162 +llama_2_70b_chat,0.15527950310559005 +gpt_neox_20b,0.14400584795321636 +vicuna_7b_v1_5,0.13619501854795973 +falcon_40b_instruct,0.13264580369843526 +gemma_7b_it,0.12136319058515854 +falcon_7b,0.11407257459889038 +gpt_j_6b,0.10160818713450293 +luminous_base_13b,0.08333333333333333 +llama_2_7b_chat,0.08304448781801049 +gemma_1_1_2b_it,0.07665903890160183 +olmo_7b,0.06545209176788123 +gemma_2b_it,0.05921052631578947 +qwen1_5_1_8b_chat,0.059167526659786716 +qwen2_0_5b_instruct,0.059081527347781215 +pythia_12b,0.054093567251461985 +pythia_6_9b,0.019736842105263157 +falcon_7b_instruct,0.013513513513513514 +qwen1_5_0_5b_chat,0.013157894736842105 diff --git a/cache/agreements_cache_2916d5df57069c497d825c9f1fac0bd4.csv b/cache/agreements_cache_2916d5df57069c497d825c9f1fac0bd4.csv new file mode 100644 index 0000000000000000000000000000000000000000..0ea572611da513f14a4c00d848f1626c1e43e2c1 --- /dev/null +++ b/cache/agreements_cache_2916d5df57069c497d825c9f1fac0bd4.csv @@ -0,0 +1,1461 @@ +scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4447495899966607,0.1315867602811863 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.47280542884465016,0.10506382347888965 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.2545875386086578,0.38281014365989596 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.40006613209931935,0.17023995462900499 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.42857142857142855,0.17886904761904762 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.18184824186332696,0.5330356744917513 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.07142857142857142,0.9048611111111111 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,-0.2857142857142857,0.39875992063492066 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.07142857142857142,0.9048611111111111 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,-0.21428571428571427,0.5484126984126985 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,-0.3571428571428571,0.27509920634920637 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,-0.2857142857142857,0.39875992063492066 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.14285714285714285,0.7195436507936508 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.0,1.0 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.07142857142857142,0.9048611111111111 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.0,1.0 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.07142857142857142,0.9048611111111111 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,-0.2857142857142857,0.39875992063492066 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.14285714285714285,0.7195436507936508 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,-0.21428571428571427,0.5484126984126985 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,-0.2857142857142857,0.39875992063492066 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,-0.2857142857142857,0.39875992063492066 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.2857142857142857,0.39875992063492066 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.0,1.0 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.07142857142857142,0.9048611111111111 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.07142857142857142,0.9048611111111111 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.21428571428571427,0.5484126984126985 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.0,1.0 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.0,1.0 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.0,1.0 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.14285714285714285,0.7195436507936508 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.14285714285714285,0.7195436507936508 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.42857142857142855,0.17886904761904762 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7637626158259734,0.008839740160738534 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7637626158259734,0.008839740160738534 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.21428571428571427,0.5484126984126985 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.14285714285714285,0.7195436507936508 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.3571428571428571,0.27509920634920637 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.2857142857142857,0.39875992063492066 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.6428571428571428,0.03115079365079365 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.21428571428571427,0.5484126984126985 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.2857142857142857,0.39875992063492066 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.21428571428571427,0.5484126984126985 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.036369648372665396,0.9007802600472398 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.21428571428571427,0.5484126984126985 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.2545875386086578,0.38281014365989596 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.6910233190806425,0.017844011512848347 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.47280542884465016,0.10506382347888965 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.21428571428571427,0.5484126984126985 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.4999999999999999,0.10868055555555556 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.42857142857142855,0.17886904761904762 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.3571428571428571,0.27509920634920637 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.3571428571428571,0.27509920634920637 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.42857142857142855,0.17886904761904762 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.2857142857142857,0.39875992063492066 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.42857142857142855,0.17886904761904762 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9999999999999998,4.96031746031746e-05 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.3571428571428571,0.27509920634920637 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9999999999999998,4.96031746031746e-05 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.4999999999999999,0.10868055555555556 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.07142857142857142,0.9048611111111111 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.14285714285714285,0.7195436507936508 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.2857142857142857,0.39875992063492066 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.3571428571428571,0.27509920634920637 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9999999999999998,4.96031746031746e-05 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9999999999999998,4.96031746031746e-05 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9999999999999998,4.96031746031746e-05 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.6910233190806425,0.017844011512848347 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6182840223353117,0.0340492747686748 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.18184824186332696,0.5330356744917513 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.42857142857142855,0.17886904761904762 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.40006613209931935,0.17023995462900499 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.2857142857142857,0.39875992063492066 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.42857142857142855,0.17886904761904762 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.2857142857142857,0.39875992063492066 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6910233190806425,0.017844011512848347 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5455447255899809,0.0614649096074132 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5455447255899809,0.0614649096074132 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.836501912571304,0.004136737098676645 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6910233190806425,0.017844011512848347 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.21428571428571427,0.5484126984126985 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.3571428571428571,0.27509920634920637 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.42857142857142855,0.17886904761904762 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.22237479499833035,0.45088703102517036 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.3571428571428571,0.27509920634920637 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.3571428571428571,0.27509920634920637 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.3571428571428571,0.27509920634920637 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.14285714285714285,0.7195436507936508 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.07142857142857142,0.9048611111111111 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,1,0.836501912571304,0.004136737098676645 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7637626158259734,0.008839740160738534 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,0,0.2857142857142857,0.39875992063492066 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,3,0.3571428571428571,0.27509920634920637 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,4,0.4999999999999999,0.10868055555555556 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,6,0.3571428571428571,0.27509920634920637 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 +LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9999999999999998,4.96031746031746e-05 +LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.47280542884465016,0.10506382347888965 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.5455447255899809,0.0614649096074132 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7637626158259734,0.008839740160738534 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.40006613209931935,0.17023995462900499 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7637626158259734,0.008839740160738534 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.3571428571428571,0.27509920634920637 +LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.6428571428571428,0.03115079365079365 +LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9999999999999998,4.96031746031746e-05 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9999999999999998,4.96031746031746e-05 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 +WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9999999999999998,4.96031746031746e-05 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9999999999999998,4.96031746031746e-05 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9999999999999998,4.96031746031746e-05 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.14285714285714285,0.7195436507936508 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,6,0.3571428571428571,0.27509920634920637 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.3571428571428571,0.27509920634920637 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,6,0.42857142857142855,0.17886904761904762 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.0,1.0 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,6,0.2857142857142857,0.39875992063492066 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,7,0.14285714285714285,0.7195436507936508 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,8,0.42857142857142855,0.17886904761904762 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.10910894511799618,0.7083840532183997 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.6182840223353117,0.0340492747686748 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.2857142857142857,0.39875992063492066 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.40006613209931935,0.17023995462900499 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,6,0.2857142857142857,0.39875992063492066 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,7,0.6182840223353117,0.0340492747686748 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,9,0.32732683535398854,0.2618277009271762 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.42857142857142855,0.17886904761904762 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.3571428571428571,0.27509920634920637 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,6,0.42857142857142855,0.17886904761904762 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,7,0.3571428571428571,0.27509920634920637 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,9,0.4999999999999999,0.10868055555555556 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.6182840223353117,0.0340492747686748 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.42857142857142855,0.17886904761904762 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.2857142857142857,0.39875992063492066 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,5,0.14285714285714285,0.7195436507936508 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,6,0.0,1.0 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,9,0.3571428571428571,0.27509920634920637 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,0,0.21428571428571427,0.5484126984126985 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,1,0.14285714285714285,0.7195436507936508 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,3,0.4999999999999999,0.10868055555555556 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,4,0.3571428571428571,0.27509920634920637 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8153742483272113,0.0057021327615243405 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.836501912571304,0.004136737098676645 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.40006613209931935,0.17023995462900499 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6910233190806425,0.017844011512848347 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.47280542884465016,0.10506382347888965 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,0.6910233190806425,0.017844011512848347 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.47280542884465016,0.10506382347888965 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6182840223353117,0.0340492747686748 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6910233190806425,0.017844011512848347 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.47280542884465016,0.10506382347888965 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7637626158259734,0.008839740160738534 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.10910894511799618,0.7083840532183997 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.3571428571428571,0.27509920634920637 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.3571428571428571,0.27509920634920637 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.47280542884465016,0.10506382347888965 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.6910233190806425,0.017844011512848347 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.4999999999999999,0.10868055555555556 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7637626158259734,0.008839740160738534 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7637626158259734,0.008839740160738534 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.6182840223353117,0.0340492747686748 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9258200997725515,0.002060881202089704 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9092412093166348,0.0018276750354536814 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,-0.2857142857142857,0.39875992063492066 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2545875386086578,0.38281014365989596 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6910233190806425,0.017844011512848347 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.10910894511799618,0.7083840532183997 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.07142857142857142,0.9048611111111111 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.07142857142857142,0.9048611111111111 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.14285714285714285,0.7195436507936508 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.2545875386086578,0.38281014365989596 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5455447255899809,0.0614649096074132 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.836501912571304,0.004136737098676645 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5669467095138409,0.05611472402809984 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6182840223353117,0.0340492747686748 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9092412093166348,0.0018276750354536814 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.40006613209931935,0.17023995462900499 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6910233190806425,0.017844011512848347 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.6910233190806425,0.017844011512848347 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.4999999999999999,0.10868055555555556 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.7412493166611012,0.011966745157436277 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7637626158259734,0.008839740160738534 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.40006613209931935,0.17023995462900499 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.6910233190806425,0.017844011512848347 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.7637626158259734,0.008839740160738534 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.42857142857142855,0.17886904761904762 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.3571428571428571,0.27509920634920637 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.6428571428571428,0.03115079365079365 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,0,0.4447495899966607,0.1315867602811863 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,2,0.47280542884465016,0.10506382347888965 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,3,0.2545875386086578,0.38281014365989596 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,4,0.40006613209931935,0.17023995462900499 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,5,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,8,0.18184824186332696,0.5330356744917513 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,0,0.07142857142857142,0.9048611111111111 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,1,-0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,2,0.07142857142857142,0.9048611111111111 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,3,-0.21428571428571427,0.5484126984126985 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,4,-0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,5,-0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,6,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,7,0.0,1.0 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,8,0.07142857142857142,0.9048611111111111 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,9,0.0,1.0 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,0,0.07142857142857142,0.9048611111111111 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,1,-0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,2,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,3,-0.21428571428571427,0.5484126984126985 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,4,-0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,5,-0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,6,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,7,0.0,1.0 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,8,0.07142857142857142,0.9048611111111111 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,9,0.07142857142857142,0.9048611111111111 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,0,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,1,0.0,1.0 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,3,0.0,1.0 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,4,0.0,1.0 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,5,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,8,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,9,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,0,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,4,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,0,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,3,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,4,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,5,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,6,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,8,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,0,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,1,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,3,0.036369648372665396,0.9007802600472398 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,4,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,5,0.2545875386086578,0.38281014365989596 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,6,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,7,0.47280542884465016,0.10506382347888965 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,8,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,9,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,9,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,3,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,4,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,5,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,8,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,9,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.07142857142857142,0.9048611111111111 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,5,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,6,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,7,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,5,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,0,0.6182840223353117,0.0340492747686748 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,1,0.18184824186332696,0.5330356744917513 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,5,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,7,0.40006613209931935,0.17023995462900499 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,9,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,6,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,7,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,0,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,1,0.5455447255899809,0.0614649096074132 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,2,0.5455447255899809,0.0614649096074132 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,3,0.836501912571304,0.004136737098676645 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,4,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,3,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,6,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,8,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,2,0.22237479499833035,0.45088703102517036 +aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,3,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,7,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,8,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,0,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,7,0.07142857142857142,0.9048611111111111 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,1,0.836501912571304,0.004136737098676645 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,9,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,0,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,3,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,4,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,6,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,7,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,2,0.47280542884465016,0.10506382347888965 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,4,0.5455447255899809,0.0614649096074132 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,7,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,8,0.40006613209931935,0.17023995462900499 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,9,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,3,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,6,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,6,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,6,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,5,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,6,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,7,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,6,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,6,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.0,1.0 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,6,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,7,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,8,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.10910894511799618,0.7083840532183997 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.6182840223353117,0.0340492747686748 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.40006613209931935,0.17023995462900499 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,6,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,7,0.6182840223353117,0.0340492747686748 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,9,0.32732683535398854,0.2618277009271762 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,6,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,7,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,9,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.6182840223353117,0.0340492747686748 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,5,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,6,0.0,1.0 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,9,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,0,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,1,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,3,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,4,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,5,0.8153742483272113,0.0057021327615243405 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,8,0.836501912571304,0.004136737098676645 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,0,0.40006613209931935,0.17023995462900499 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,1,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,4,0.47280542884465016,0.10506382347888965 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,5,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,6,0.47280542884465016,0.10506382347888965 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,7,0.6182840223353117,0.0340492747686748 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,8,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,0,0.47280542884465016,0.10506382347888965 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,2,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,4,0.10910894511799618,0.7083840532183997 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,6,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,7,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,8,0.47280542884465016,0.10506382347888965 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,9,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,9,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,1,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,4,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,6,0.6182840223353117,0.0340492747686748 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,7,0.9258200997725515,0.002060881202089704 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,8,0.9092412093166348,0.0018276750354536814 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,0,-0.2857142857142857,0.39875992063492066 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,1,0.2545875386086578,0.38281014365989596 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,2,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,3,0.10910894511799618,0.7083840532183997 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,4,0.07142857142857142,0.9048611111111111 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,6,0.07142857142857142,0.9048611111111111 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,7,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,8,0.2545875386086578,0.38281014365989596 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,9,0.5455447255899809,0.0614649096074132 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,2,0.836501912571304,0.004136737098676645 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,3,0.5669467095138409,0.05611472402809984 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,4,0.6182840223353117,0.0340492747686748 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,5,0.9092412093166348,0.0018276750354536814 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,6,0.40006613209931935,0.17023995462900499 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,8,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,9,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,9,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,0,0.7412493166611012,0.011966745157436277 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,2,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,5,0.40006613209931935,0.17023995462900499 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,9,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,4,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,5,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,8,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,6,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,9,0.42857142857142855,0.17886904761904762 diff --git a/cache/agreements_cache_e798cd9f99d4c09af5b81734eecc6592.csv b/cache/agreements_cache_e798cd9f99d4c09af5b81734eecc6592.csv index ba35cb3adcb3db1caaa845f056a02204ab1e897b..ad15d7feb3a14a1b271d0ef6f392258cdbb688de 100644 --- a/cache/agreements_cache_e798cd9f99d4c09af5b81734eecc6592.csv +++ b/cache/agreements_cache_e798cd9f99d4c09af5b81734eecc6592.csv @@ -1,801 +1,2001 @@ scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value -HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 -HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 -HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +Holmes,holmes_240829.csv,aggregate,aggregate,kendall,random,8,0,-0.14285714285714285,0.7195436507936508 +Holmes,holmes_240829.csv,aggregate,aggregate,kendall,random,8,1,-0.14285714285714285,0.7195436507936508 +Holmes,holmes_240829.csv,aggregate,aggregate,kendall,random,8,2,-0.2857142857142857,0.39875992063492066 +Holmes,holmes_240829.csv,aggregate,aggregate,kendall,random,8,3,-0.21428571428571427,0.5484126984126985 +Holmes,holmes_240829.csv,aggregate,aggregate,kendall,random,8,4,-0.07142857142857142,0.9048611111111111 +Holmes,holmes_240829.csv,aggregate,aggregate,kendall,random,8,5,-0.3571428571428571,0.27509920634920637 +Holmes,holmes_240829.csv,aggregate,aggregate,kendall,random,8,6,-0.3571428571428571,0.27509920634920637 +Holmes,holmes_240829.csv,aggregate,aggregate,kendall,random,8,7,-0.2857142857142857,0.39875992063492066 +Holmes,holmes_240829.csv,aggregate,aggregate,kendall,random,8,8,-0.07142857142857142,0.9048611111111111 +Holmes,holmes_240829.csv,aggregate,aggregate,kendall,random,8,9,-0.14285714285714285,0.7195436507936508 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6182840223353117,0.0340492747686748 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,-0.07142857142857142,0.9048611111111111 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,-0.3571428571428571,0.27509920634920637 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,-0.07142857142857142,0.9048611111111111 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.21428571428571427,0.5484126984126985 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,-0.3571428571428571,0.27509920634920637 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.3571428571428571,0.27509920634920637 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,-0.07142857142857142,0.9048611111111111 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.2857142857142857,0.39875992063492066 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.07142857142857142,0.9048611111111111 +Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.3571428571428571,0.27509920634920637 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.2857142857142857,0.39875992063492066 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.0,1.0 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.14285714285714285,0.7195436507936508 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.2857142857142857,0.39875992063492066 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.10910894511799618,0.7083840532183997 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.21428571428571427,0.5484126984126985 +Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.3571428571428571,0.27509920634920637 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.42857142857142855,0.17886904761904762 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.6910233190806425,0.017844011512848347 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.21428571428571427,0.5484126984126985 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.2545875386086578,0.38281014365989596 +Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.2857142857142857,0.39875992063492066 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9999999999999998,4.96031746031746e-05 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7637626158259734,0.008839740160738534 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.42857142857142855,0.17886904761904762 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.42857142857142855,0.17886904761904762 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5455447255899809,0.0614649096074132 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7637626158259734,0.008839740160738534 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.3571428571428571,0.27509920634920637 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5455447255899809,0.0614649096074132 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9092412093166348,0.0018276750354536814 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9092412093166348,0.0018276750354536814 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,7,0.3571428571428571,0.27509920634920637 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 -HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 -HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 -HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 -HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 -HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7637626158259734,0.008839740160738534 HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 -HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 -HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556 -HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556 -HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556 -HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.4999999999999999,0.10868055555555556 -HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.4999999999999999,0.10868055555555556 -HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.4999999999999999,0.10868055555555556 -HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.4999999999999999,0.10868055555555556 -HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.4999999999999999,0.10868055555555556 -HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 -HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.4999999999999999,0.10868055555555556 -HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 -HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 -HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 -HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 -HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 -HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 -HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 -HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 -HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 -HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 -HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3401680257083045,0.25175949861106117 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.836501912571304,0.004136737098676645 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.18184824186332696,0.5330356744917513 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.836501912571304,0.004136737098676645 +HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.0,1.0 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.14285714285714285,0.7195436507936508 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.42857142857142855,0.17886904761904762 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.4999999999999999,0.10868055555555556 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,-0.07142857142857142,0.9048611111111111 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 -HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 -HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 -HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.3706246583305506,0.20891238174069848 -HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3706246583305506,0.20891238174069848 -HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3706246583305506,0.20891238174069848 -HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.3706246583305506,0.20891238174069848 -HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.3706246583305506,0.20891238174069848 -HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.3706246583305506,0.20891238174069848 -HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.3706246583305506,0.20891238174069848 -HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.3706246583305506,0.20891238174069848 -HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.3706246583305506,0.20891238174069848 -HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.3706246583305506,0.20891238174069848 -HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 -HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 -HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476 -HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.21428571428571427,0.5484126984126985 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5455447255899809,0.0614649096074132 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.18184824186332696,0.5330356744917513 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.2545875386086578,0.38281014365989596 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.18184824186332696,0.5330356744917513 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.3571428571428571,0.27509920634920637 +HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.42857142857142855,0.17886904761904762 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.10910894511799618,0.7083840532183997 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.21428571428571427,0.5484126984126985 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.21428571428571427,0.5484126984126985 HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.5714285714285714,0.06101190476190476 -HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 -HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 -HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,7,-0.3571428571428571,0.27509920634920637 +HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 -LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 -LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9999999999999998,4.96031746031746e-05 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +OpenCompass Academic,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +OpenCompass MMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +OpenCompass MMLU Pro,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +OpenCompass CMMLU,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +OpenCompass BBH,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6910233190806425,0.017844011512848347 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.42857142857142855,0.17886904761904762 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.40006613209931935,0.17023995462900499 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9092412093166348,0.0018276750354536814 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5929994533288809,0.04437842734548688 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6910233190806425,0.017844011512848347 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5455447255899809,0.0614649096074132 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6910233190806425,0.017844011512848347 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.47280542884465016,0.10506382347888965 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.49135381491199537,0.09783166898477644 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.49135381491199537,0.09783166898477644 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6910233190806425,0.017844011512848347 +OpenCompass HumanEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.6182840223353117,0.0340492747686748 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.2857142857142857,0.39875992063492066 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +OpenCompass IFEval,opencompass_academic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9092412093166348,0.0018276750354536814 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,7,0.2857142857142857,0.39875992063492066 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,8,0.3571428571428571,0.27509920634920637 +Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 -LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 -LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 -MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 -MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 +Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9999999999999998,4.96031746031746e-05 +Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +Helm Classic,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.4999999999999999,0.10868055555555556 +Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +Helm BoolQ,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762 +Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.4999999999999999,0.10868055555555556 +Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +Helm NarrativeQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +Helm NaturalQuestionsClosed,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6910233190806425,0.017844011512848347 +Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7637626158259734,0.008839740160738534 +Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6910233190806425,0.017844011512848347 +Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +Helm NaturalQuestionsOpen,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.21428571428571427,0.5484126984126985 +Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637 +Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.3571428571428571,0.27509920634920637 +Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +Helm QuAC,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.07142857142857142,0.9048611111111111 +Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +Helm OpenBookQA,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.4999999999999999,0.10868055555555556 +Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.21428571428571427,0.5484126984126985 +Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762 +Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3706246583305506,0.20891238174069848 +Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.3571428571428571,0.27509920634920637 +Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.40006613209931935,0.17023995462900499 +Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.3571428571428571,0.27509920634920637 +Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.5455447255899809,0.0614649096074132 +Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.07142857142857142,0.9048611111111111 +Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.47280542884465016,0.10506382347888965 +Helm IMDB,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.2857142857142857,0.39875992063492066 +Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762 +Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.42857142857142855,0.17886904761904762 +Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +Helm CivilComments,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5455447255899809,0.0614649096074132 +Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,5,0.6910233190806425,0.017844011512848347 +Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,6,0.6910233190806425,0.017844011512848347 +Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +Helm RAFT,helm_classic_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365 -MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 -MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 -MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 -MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 -MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9819805060619657,0.0007619896395304237 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 -MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 -MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637 MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 -MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 -MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 -MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 -MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 -MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 -MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.4999999999999999,0.10868055555555556 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.6428571428571428,0.03115079365079365 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 -MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 -MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 -MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365 -MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 -MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 -MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.6428571428571428,0.03115079365079365 -MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 -MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.4999999999999999,0.10868055555555556 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.0,1.0 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.3571428571428571,0.27509920634920637 MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.6428571428571428,0.03115079365079365 -MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 -MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 -MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 -MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 -MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 -MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 -MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 -MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 -MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 -MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556 MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 -MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365 -MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 -MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.4999999999999999,0.10868055555555556 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.2857142857142857,0.39875992063492066 MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.6428571428571428,0.03115079365079365 -MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 -MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 -MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 -MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 -MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 -MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 -MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.42857142857142855,0.17886904761904762 -MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.42857142857142855,0.17886904761904762 -MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 -MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 -MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.42857142857142855,0.17886904761904762 -MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.2857142857142857,0.39875992063492066 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6910233190806425,0.017844011512848347 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.6910233190806425,0.017844011512848347 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.42857142857142855,0.17886904761904762 MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.6428571428571428,0.03115079365079365 -MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.836501912571304,0.004136737098676645 -MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6910233190806425,0.017844011512848347 -MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6910233190806425,0.017844011512848347 -MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5929994533288809,0.04437842734548688 -MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.5929994533288809,0.04437842734548688 -MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.6671243849949912,0.02370907646413876 -MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.6910233190806425,0.017844011512848347 -MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5929994533288809,0.04437842734548688 -MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6671243849949912,0.02370907646413876 -MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.6910233190806425,0.017844011512848347 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6182840223353117,0.0340492747686748 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9092412093166348,0.0018276750354536814 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.6428571428571428,0.03115079365079365 MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 -MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637 MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 -MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 -MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.3571428571428571,0.27509920634920637 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 -MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 -MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 -MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.22237479499833035,0.45088703102517036 MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 -MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.2545875386086578,0.38281014365989596 MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 -MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 -MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 -MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.40006613209931935,0.17023995462900499 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6182840223353117,0.0340492747686748 +MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.42857142857142855,0.17886904761904762 MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 -MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 -MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 -MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5455447255899809,0.0614649096074132 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7637626158259734,0.008839740160738534 MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 -MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.5714285714285714,0.06101190476190476 -MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 -MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.6428571428571428,0.03115079365079365 -MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 -MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 -MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.6428571428571428,0.03115079365079365 -LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 -LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 -LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 -LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.14285714285714285,0.7195436507936508 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9999999999999998,4.96031746031746e-05 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,6,0.42857142857142855,0.17886904761904762 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9092412093166348,0.0018276750354536814 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7637626158259734,0.008839740160738534 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +OpenCompass,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +OpenCompass Language,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +OpenCompass Language,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.0,1.0 +OpenCompass Language,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637 +OpenCompass Language,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,3,0.42857142857142855,0.17886904761904762 +OpenCompass Language,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,4,0.21428571428571427,0.5484126984126985 +OpenCompass Language,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +OpenCompass Language,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,6,0.21428571428571427,0.5484126984126985 +OpenCompass Language,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +OpenCompass Language,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,8,0.21428571428571427,0.5484126984126985 +OpenCompass Language,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,9,0.0,1.0 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,3,0.2857142857142857,0.39875992063492066 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,5,0.42857142857142855,0.17886904761904762 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +OpenCompass Knowledge,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,9,0.21428571428571427,0.5484126984126985 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +OpenCompass Reasoning,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,9,0.2857142857142857,0.39875992063492066 +OpenCompass Math,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +OpenCompass Math,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +OpenCompass Math,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +OpenCompass Math,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +OpenCompass Math,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +OpenCompass Math,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +OpenCompass Math,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +OpenCompass Math,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +OpenCompass Math,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +OpenCompass Math,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +OpenCompass Code,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +OpenCompass Code,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +OpenCompass Code,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,0.47280542884465016,0.10506382347888965 +OpenCompass Code,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +OpenCompass Code,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +OpenCompass Code,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +OpenCompass Code,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +OpenCompass Code,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +OpenCompass Code,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,8,0.836501912571304,0.004136737098676645 +OpenCompass Code,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,9,0.3571428571428571,0.27509920634920637 +OpenCompass Instruction,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +OpenCompass Instruction,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +OpenCompass Instruction,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +OpenCompass Instruction,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +OpenCompass Instruction,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +OpenCompass Instruction,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,5,0.3571428571428571,0.27509920634920637 +OpenCompass Instruction,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +OpenCompass Instruction,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +OpenCompass Instruction,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +OpenCompass Instruction,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +OpenCompass Agent,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637 +OpenCompass Agent,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762 +OpenCompass Agent,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,2,0.2857142857142857,0.39875992063492066 +OpenCompass Agent,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,3,0.21428571428571427,0.5484126984126985 +OpenCompass Agent,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +OpenCompass Agent,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,5,0.3571428571428571,0.27509920634920637 +OpenCompass Agent,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,6,0.42857142857142855,0.17886904761904762 +OpenCompass Agent,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,7,0.14285714285714285,0.7195436507936508 +OpenCompass Agent,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +OpenCompass Agent,opencompass_240829.csv,aggregate,aggregate,kendall,random,8,9,0.2857142857142857,0.39875992063492066 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,0,0.3571428571428571,0.27509920634920637 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,1,0.14285714285714285,0.7195436507936508 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,3,0.4999999999999999,0.10868055555555556 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,4,0.2857142857142857,0.39875992063492066 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,5,0.5455447255899809,0.0614649096074132 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6910233190806425,0.017844011512848347 +OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,9,0.32732683535398854,0.2618277009271762 +LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 -LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 -LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6910233190806425,0.017844011512848347 -LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9819805060619657,0.0007619896395304237 -LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 -LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9819805060619657,0.0007619896395304237 -LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9092412093166348,0.0018276750354536814 -LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9819805060619657,0.0007619896395304237 -LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 -LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9092412093166348,0.0018276750354536814 -LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 -LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 -LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 -LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.836501912571304,0.004136737098676645 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5455447255899809,0.0614649096074132 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.836501912571304,0.004136737098676645 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 -LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 -LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 -LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 -LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 -LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 -LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 -LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 -LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 -LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9999999999999998,4.96031746031746e-05 -LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9999999999999998,4.96031746031746e-05 +LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 -LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 -LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 -LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476 -LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.3571428571428571,0.27509920634920637 -LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 -LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.4999999999999999,0.10868055555555556 -LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.3571428571428571,0.27509920634920637 -LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.42857142857142855,0.17886904761904762 -LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 -LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.4999999999999999,0.10868055555555556 -LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762 -LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 -LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 -LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9819805060619657,0.0007619896395304237 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9092412093166348,0.0018276750354536814 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 -LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 -LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.6428571428571428,0.03115079365079365 -LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 -LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 -LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 -LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 -LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365 -LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.4999999999999999,0.10868055555555556 -LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.4999999999999999,0.10868055555555556 -LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.4999999999999999,0.10868055555555556 -WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 -WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 -WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 -WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 -WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 -WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 -WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 -WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 -WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 -WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 -WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.9999999999999998,4.96031746031746e-05 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 -WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 -WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7142857142857142,0.014136904761904762 -WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 -WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 -WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 -WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 -WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 -WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.4999999999999999,0.10868055555555556 WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 -WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.6428571428571428,0.03115079365079365 -WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 -WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 -WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.5714285714285714,0.06101190476190476 -WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.836501912571304,0.004136737098676645 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 -WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 -WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 -WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 -WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 -WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 -WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 -WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.836501912571304,0.004136737098676645 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 -WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7637626158259734,0.008839740160738534 WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 -WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 -WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 -WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 -WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 -WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 -WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05 +WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 -WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 -WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 -Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 -Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 -Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 -Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.3571428571428571,0.27509920634920637 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,5,0.21428571428571427,0.5484126984126985 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,9,0.6910233190806425,0.017844011512848347 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.5455447255899809,0.0614649096074132 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.2857142857142857,0.39875992063492066 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.4999999999999999,0.10868055555555556 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,5,0.14285714285714285,0.7195436507936508 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.42857142857142855,0.17886904761904762 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.21428571428571427,0.5484126984126985 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,5,0.21428571428571427,0.5484126984126985 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,6,0.3571428571428571,0.27509920634920637 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,7,0.07142857142857142,0.9048611111111111 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.14285714285714285,0.7195436507936508 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.4999999999999999,0.10868055555555556 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,5,0.2857142857142857,0.39875992063492066 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,9,0.2857142857142857,0.39875992063492066 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.21428571428571427,0.5484126984126985 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.2857142857142857,0.39875992063492066 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,-0.07142857142857142,0.9048611111111111 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.21428571428571427,0.5484126984126985 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,5,0.2857142857142857,0.39875992063492066 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,6,0.2857142857142857,0.39875992063492066 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,7,0.2857142857142857,0.39875992063492066 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,8,0.42857142857142855,0.17886904761904762 +HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,9,0.42857142857142855,0.17886904761904762 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.14285714285714285,0.7195436507936508 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.47280542884465016,0.10506382347888965 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,5,0.2545875386086578,0.38281014365989596 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,6,0.6428571428571428,0.03115079365079365 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,9,0.42857142857142855,0.17886904761904762 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,3,0.2857142857142857,0.39875992063492066 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,4,0.4999999999999999,0.10868055555555556 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,6,0.42857142857142855,0.17886904761904762 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +bfcl,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,9,0.2857142857142857,0.39875992063492066 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.21428571428571427,0.5484126984126985 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,-0.3571428571428571,0.27509920634920637 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,-0.14285714285714285,0.7195436507936508 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.3571428571428571,0.27509920634920637 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.0,1.0 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.47280542884465016,0.10506382347888965 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.3571428571428571,0.27509920634920637 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.18184824186332696,0.5330356744917513 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,-0.14285714285714285,0.7195436507936508 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.836501912571304,0.004136737098676645 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.2545875386086578,0.38281014365989596 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.10910894511799618,0.7083840532183997 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,-0.40006613209931935,0.17023995462900499 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,-0.2857142857142857,0.39875992063492066 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.836501912571304,0.004136737098676645 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,-0.14285714285714285,0.7195436507936508 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.47280542884465016,0.10506382347888965 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6182840223353117,0.0340492747686748 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5455447255899809,0.0614649096074132 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.21428571428571427,0.5484126984126985 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,-0.42857142857142855,0.17886904761904762 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,-0.21428571428571427,0.5484126984126985 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.2857142857142857,0.39875992063492066 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.07142857142857142,0.9048611111111111 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.2857142857142857,0.39875992063492066 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.0,1.0 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,-0.14285714285714285,0.7195436507936508 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.47280542884465016,0.10506382347888965 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.21428571428571427,0.5484126984126985 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.21428571428571427,0.5484126984126985 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,-0.07142857142857142,0.9048611111111111 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,-0.07142857142857142,0.9048611111111111 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.2857142857142857,0.39875992063492066 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.21428571428571427,0.5484126984126985 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.2857142857142857,0.39875992063492066 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.14285714285714285,0.7195436507936508 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,-0.14285714285714285,0.7195436507936508 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,-0.42857142857142855,0.17886904761904762 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,0.0,1.0 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.47280542884465016,0.10506382347888965 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.40006613209931935,0.17023995462900499 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.21428571428571427,0.5484126984126985 +BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,-0.5714285714285714,0.06101190476190476 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.21428571428571427,0.5484126984126985 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,-0.2545875386086578,0.38281014365989596 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,-0.21428571428571427,0.5484126984126985 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.21428571428571427,0.5484126984126985 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,-0.07142857142857142,0.9048611111111111 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.18184824186332696,0.5330356744917513 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,-0.21428571428571427,0.5484126984126985 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,-0.2857142857142857,0.39875992063492066 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.2857142857142857,0.39875992063492066 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.21428571428571427,0.5484126984126985 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7637626158259734,0.008839740160738534 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6910233190806425,0.017844011512848347 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,7,0.7637626158259734,0.008839740160738534 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 -LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 -LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 -LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 -LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 -LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 -LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.6910233190806425,0.017844011512848347 -LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 -LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.6182840223353117,0.0340492747686748 -LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 -LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 -LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 -LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.7142857142857142,0.014136904761904762 -LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.7637626158259734,0.008839740160738534 -LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.7637626158259734,0.008839740160738534 -LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.7637626158259734,0.008839740160738534 -LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 -LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381 -LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 -LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.6910233190806425,0.017844011512848347 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.836501912571304,0.004136737098676645 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.6182840223353117,0.0340492747686748 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.7637626158259734,0.008839740160738534 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 -LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.9092412093166348,0.0018276750354536814 LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 -LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 -LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111 -LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 -LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 -LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.9999999999999998,4.96031746031746e-05 -LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 -LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 -LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762 -LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.21428571428571427,0.5484126984126985 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.9999999999999998,4.96031746031746e-05 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111 LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 -LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 -LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.4999999999999999,0.10868055555555556 -LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.3571428571428571,0.27509920634920637 -LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.42857142857142855,0.17886904761904762 -LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.3571428571428571,0.27509920634920637 -LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 -LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.42857142857142855,0.17886904761904762 -LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365 -LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365 -LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762 -LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476 -LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 -LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.5714285714285714,0.06101190476190476 -LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.6428571428571428,0.03115079365079365 -LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.5714285714285714,0.06101190476190476 -LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.5714285714285714,0.06101190476190476 -LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 -LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 -LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.6182840223353117,0.0340492747686748 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556 LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365 -LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762 -LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111 -LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.6428571428571428,0.03115079365079365 -LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.5714285714285714,0.06101190476190476 -LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.6428571428571428,0.03115079365079365 -LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.8571428571428571,0.001736111111111111 -LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,7,0.3571428571428571,0.27509920634920637 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Holmes,holmes_240829.csv,kendall,random,8,0,-0.14285714285714285,0.7195436507936508 +aggregate,aggregate,Holmes,holmes_240829.csv,kendall,random,8,1,-0.14285714285714285,0.7195436507936508 +aggregate,aggregate,Holmes,holmes_240829.csv,kendall,random,8,2,-0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Holmes,holmes_240829.csv,kendall,random,8,3,-0.21428571428571427,0.5484126984126985 +aggregate,aggregate,Holmes,holmes_240829.csv,kendall,random,8,4,-0.07142857142857142,0.9048611111111111 +aggregate,aggregate,Holmes,holmes_240829.csv,kendall,random,8,5,-0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Holmes,holmes_240829.csv,kendall,random,8,6,-0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Holmes,holmes_240829.csv,kendall,random,8,7,-0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Holmes,holmes_240829.csv,kendall,random,8,8,-0.07142857142857142,0.9048611111111111 +aggregate,aggregate,Holmes,holmes_240829.csv,kendall,random,8,9,-0.14285714285714285,0.7195436507936508 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,1,0.6182840223353117,0.0340492747686748 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,0,-0.07142857142857142,0.9048611111111111 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,1,-0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,2,-0.07142857142857142,0.9048611111111111 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,3,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,4,-0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,5,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,6,-0.07142857142857142,0.9048611111111111 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,7,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,8,0.07142857142857142,0.9048611111111111 +aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,9,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,0,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,1,0.0,1.0 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,3,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,4,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,5,0.10910894511799618,0.7083840532183997 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,8,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,9,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,3,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,6,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,7,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,8,0.2545875386086578,0.38281014365989596 +aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,9,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,6,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,9,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,9,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,3,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,2,0.5455447255899809,0.0614649096074132 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,3,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,7,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,1,0.5455447255899809,0.0614649096074132 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,6,0.9092412093166348,0.0018276750354536814 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,4,0.9092412093166348,0.0018276750354536814 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,7,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.7637626158259734,0.008839740160738534 aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556 -aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556 -aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556 -aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.4999999999999999,0.10868055555555556 -aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.4999999999999999,0.10868055555555556 -aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.4999999999999999,0.10868055555555556 -aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.4999999999999999,0.10868055555555556 -aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.4999999999999999,0.10868055555555556 -aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 -aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.4999999999999999,0.10868055555555556 -aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.3401680257083045,0.25175949861106117 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.836501912571304,0.004136737098676645 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.18184824186332696,0.5330356744917513 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.836501912571304,0.004136737098676645 +aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.0,1.0 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,9,-0.07142857142857142,0.9048611111111111 +aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.3706246583305506,0.20891238174069848 -aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.3706246583305506,0.20891238174069848 -aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.3706246583305506,0.20891238174069848 -aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.3706246583305506,0.20891238174069848 -aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.3706246583305506,0.20891238174069848 -aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.3706246583305506,0.20891238174069848 -aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.3706246583305506,0.20891238174069848 -aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.3706246583305506,0.20891238174069848 -aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.3706246583305506,0.20891238174069848 -aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.3706246583305506,0.20891238174069848 -aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.5455447255899809,0.0614649096074132 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.18184824186332696,0.5330356744917513 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.2545875386086578,0.38281014365989596 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.18184824186332696,0.5330356744917513 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.10910894511799618,0.7083840532183997 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.21428571428571427,0.5484126984126985 aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,7,-0.3571428571428571,0.27509920634920637 +aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,8,7,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass Academic,opencompass_academic_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass MMLU,opencompass_academic_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass MMLU Pro,opencompass_academic_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,OpenCompass CMMLU,opencompass_academic_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass BBH,opencompass_academic_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,8,1,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,8,3,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,8,4,0.40006613209931935,0.17023995462900499 +aggregate,aggregate,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,8,6,0.9092412093166348,0.0018276750354536814 +aggregate,aggregate,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,OpenCompass GQPA-Dimand,opencompass_academic_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,8,1,0.5929994533288809,0.04437842734548688 +aggregate,aggregate,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,8,2,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,8,3,0.5455447255899809,0.0614649096074132 +aggregate,aggregate,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,8,4,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,8,5,0.47280542884465016,0.10506382347888965 +aggregate,aggregate,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,8,6,0.49135381491199537,0.09783166898477644 +aggregate,aggregate,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,8,7,0.49135381491199537,0.09783166898477644 +aggregate,aggregate,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,8,8,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,OpenCompass HumanEval,opencompass_academic_240829.csv,kendall,random,8,9,0.6182840223353117,0.0340492747686748 +aggregate,aggregate,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,8,7,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,OpenCompass IFEval,opencompass_academic_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,5,0.9092412093166348,0.0018276750354536814 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,7,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,8,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,8,7,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Helm Classic,helm_classic_240829.csv,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,8,4,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,Helm BoolQ,helm_classic_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,8,4,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm NarrativeQA,helm_classic_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Helm NaturalQuestionsClosed,helm_classic_240829.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,8,0,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,8,4,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,8,7,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm NaturalQuestionsOpen,helm_classic_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,8,0,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,8,6,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm QuAC,helm_classic_240829.csv,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,8,2,0.07142857142857142,0.9048611111111111 +aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Helm OpenBookQA,helm_classic_240829.csv,kendall,random,8,9,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,8,0,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,8,2,0.3706246583305506,0.20891238174069848 +aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,8,3,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,8,4,0.40006613209931935,0.17023995462900499 +aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,8,5,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,8,6,0.5455447255899809,0.0614649096074132 +aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,8,7,0.07142857142857142,0.9048611111111111 +aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,8,8,0.47280542884465016,0.10506382347888965 +aggregate,aggregate,Helm IMDB,helm_classic_240829.csv,kendall,random,8,9,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,8,6,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm CivilComments,helm_classic_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,8,1,0.5455447255899809,0.0614649096074132 +aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,8,5,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,8,6,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,Helm RAFT,helm_classic_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,6,0.9819805060619657,0.0007619896395304237 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637 aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,4,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,6,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,6,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,3,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,5,0.0,1.0 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,8,0.3571428571428571,0.27509920634920637 aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,9,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556 aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,3,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,5,0.2857142857142857,0.39875992063492066 aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,6,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,3,0.42857142857142855,0.17886904761904762 -aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,4,0.42857142857142855,0.17886904761904762 -aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,7,0.42857142857142855,0.17886904761904762 -aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,9,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,2,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,5,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,8,0.42857142857142855,0.17886904761904762 aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,9,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,0,0.836501912571304,0.004136737098676645 -aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,1,0.6910233190806425,0.017844011512848347 -aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,2,0.6910233190806425,0.017844011512848347 -aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,3,0.5929994533288809,0.04437842734548688 -aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,4,0.5929994533288809,0.04437842734548688 -aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,5,0.6671243849949912,0.02370907646413876 -aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,6,0.6910233190806425,0.017844011512848347 -aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,7,0.5929994533288809,0.04437842734548688 -aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,8,0.6671243849949912,0.02370907646413876 -aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,9,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,3,0.6182840223353117,0.0340492747686748 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,6,0.9092412093166348,0.0018276750354536814 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,9,0.6428571428571428,0.03115079365079365 aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637 aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,4,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,1,0.22237479499833035,0.45088703102517036 aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,4,0.2545875386086578,0.38281014365989596 aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,6,0.40006613209931935,0.17023995462900499 +aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,7,0.6182840223353117,0.0340492747686748 +aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,8,0.42857142857142855,0.17886904761904762 aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,0,0.5455447255899809,0.0614649096074132 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,2,0.7637626158259734,0.008839740160738534 aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,4,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,6,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,9,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,4,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,5,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,6,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,0,0.9092412093166348,0.0018276750354536814 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,1,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,OpenCompass,opencompass_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass Language,opencompass_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,OpenCompass Language,opencompass_240829.csv,kendall,random,8,1,0.0,1.0 +aggregate,aggregate,OpenCompass Language,opencompass_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,OpenCompass Language,opencompass_240829.csv,kendall,random,8,3,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,OpenCompass Language,opencompass_240829.csv,kendall,random,8,4,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,OpenCompass Language,opencompass_240829.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,OpenCompass Language,opencompass_240829.csv,kendall,random,8,6,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,OpenCompass Language,opencompass_240829.csv,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,OpenCompass Language,opencompass_240829.csv,kendall,random,8,8,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,OpenCompass Language,opencompass_240829.csv,kendall,random,8,9,0.0,1.0 +aggregate,aggregate,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,8,3,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,8,5,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass Knowledge,opencompass_240829.csv,kendall,random,8,9,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,OpenCompass Reasoning,opencompass_240829.csv,kendall,random,8,9,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,OpenCompass Math,opencompass_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,OpenCompass Math,opencompass_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass Math,opencompass_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass Math,opencompass_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass Math,opencompass_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass Math,opencompass_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass Math,opencompass_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,OpenCompass Math,opencompass_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass Math,opencompass_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass Math,opencompass_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass Code,opencompass_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass Code,opencompass_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,OpenCompass Code,opencompass_240829.csv,kendall,random,8,2,0.47280542884465016,0.10506382347888965 +aggregate,aggregate,OpenCompass Code,opencompass_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass Code,opencompass_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass Code,opencompass_240829.csv,kendall,random,8,5,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,OpenCompass Code,opencompass_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,OpenCompass Code,opencompass_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass Code,opencompass_240829.csv,kendall,random,8,8,0.836501912571304,0.004136737098676645 +aggregate,aggregate,OpenCompass Code,opencompass_240829.csv,kendall,random,8,9,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,OpenCompass Instruction,opencompass_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,OpenCompass Instruction,opencompass_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass Instruction,opencompass_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,OpenCompass Instruction,opencompass_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass Instruction,opencompass_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass Instruction,opencompass_240829.csv,kendall,random,8,5,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,OpenCompass Instruction,opencompass_240829.csv,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,OpenCompass Instruction,opencompass_240829.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,OpenCompass Instruction,opencompass_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,OpenCompass Instruction,opencompass_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,OpenCompass Agent,opencompass_240829.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,OpenCompass Agent,opencompass_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,OpenCompass Agent,opencompass_240829.csv,kendall,random,8,2,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,OpenCompass Agent,opencompass_240829.csv,kendall,random,8,3,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,OpenCompass Agent,opencompass_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass Agent,opencompass_240829.csv,kendall,random,8,5,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,OpenCompass Agent,opencompass_240829.csv,kendall,random,8,6,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,OpenCompass Agent,opencompass_240829.csv,kendall,random,8,7,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,OpenCompass Agent,opencompass_240829.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,OpenCompass Agent,opencompass_240829.csv,kendall,random,8,9,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,0,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,1,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,3,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,4,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,5,0.5455447255899809,0.0614649096074132 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,6,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,8,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,9,0.32732683535398854,0.2618277009271762 +aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,0,0.6910233190806425,0.017844011512848347 -aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,1,0.9819805060619657,0.0007619896395304237 -aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,3,0.9819805060619657,0.0007619896395304237 -aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,4,0.9092412093166348,0.0018276750354536814 -aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,5,0.9819805060619657,0.0007619896395304237 -aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,7,0.9092412093166348,0.0018276750354536814 -aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,1,0.836501912571304,0.004136737098676645 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,2,0.5455447255899809,0.0614649096074132 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,6,0.836501912571304,0.004136737098676645 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 -aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 -aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,5,0.9999999999999998,4.96031746031746e-05 -aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,7,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,3,0.3571428571428571,0.27509920634920637 -aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,5,0.4999999999999999,0.10868055555555556 -aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,6,0.3571428571428571,0.27509920634920637 -aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,7,0.42857142857142855,0.17886904761904762 -aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,9,0.4999999999999999,0.10868055555555556 -aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762 -aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,0,0.9819805060619657,0.0007619896395304237 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,9,0.9092412093166348,0.0018276750354536814 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,6,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,4,0.4999999999999999,0.10868055555555556 -aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,7,0.4999999999999999,0.10868055555555556 -aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,9,0.4999999999999999,0.10868055555555556 -aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,6,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,7,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,4,0.4999999999999999,0.10868055555555556 aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,6,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,9,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,6,0.836501912571304,0.004136737098676645 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,9,0.836501912571304,0.004136737098676645 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,9,0.7637626158259734,0.008839740160738534 aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,5,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,9,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.5455447255899809,0.0614649096074132 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,5,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,9,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,5,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,6,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,7,0.07142857142857142,0.9048611111111111 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,9,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,5,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,9,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,5,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,-0.07142857142857142,0.9048611111111111 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,5,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,6,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,7,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,8,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,9,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.47280542884465016,0.10506382347888965 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,5,0.2545875386086578,0.38281014365989596 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,6,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,9,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,3,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,4,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,6,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,7,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,8,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,bfcl,bfcl_240906.csv,kendall,random,8,9,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,3,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,4,-0.3571428571428571,0.27509920634920637 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,5,-0.14285714285714285,0.7195436507936508 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,7,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,9,0.0,1.0 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,2,0.47280542884465016,0.10506382347888965 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,3,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,4,0.18184824186332696,0.5330356744917513 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,5,-0.14285714285714285,0.7195436507936508 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,6,0.836501912571304,0.004136737098676645 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,9,0.2545875386086578,0.38281014365989596 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,3,0.10910894511799618,0.7083840532183997 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,4,-0.40006613209931935,0.17023995462900499 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,5,-0.2857142857142857,0.39875992063492066 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,6,0.836501912571304,0.004136737098676645 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,7,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,8,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,9,-0.14285714285714285,0.7195436507936508 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,0,0.47280542884465016,0.10506382347888965 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,1,0.6182840223353117,0.0340492747686748 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,2,0.5455447255899809,0.0614649096074132 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,3,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,4,-0.42857142857142855,0.17886904761904762 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,5,-0.21428571428571427,0.5484126984126985 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,7,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,9,0.07142857142857142,0.9048611111111111 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,3,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,4,0.0,1.0 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,5,-0.14285714285714285,0.7195436507936508 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,7,0.47280542884465016,0.10506382347888965 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,9,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,3,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,4,-0.07142857142857142,0.9048611111111111 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,5,-0.07142857142857142,0.9048611111111111 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,7,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,9,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,0,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,2,0.14285714285714285,0.7195436507936508 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,3,-0.14285714285714285,0.7195436507936508 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,4,-0.42857142857142855,0.17886904761904762 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,5,0.0,1.0 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,6,0.47280542884465016,0.10506382347888965 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,7,0.40006613209931935,0.17023995462900499 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,8,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,9,-0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,3,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,4,-0.2545875386086578,0.38281014365989596 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,5,-0.21428571428571427,0.5484126984126985 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,7,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,9,-0.07142857142857142,0.9048611111111111 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,3,0.18184824186332696,0.5330356744917513 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,4,-0.21428571428571427,0.5484126984126985 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,5,-0.2857142857142857,0.39875992063492066 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,7,0.2857142857142857,0.39875992063492066 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,9,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,2,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,3,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,7,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05 -aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,5,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,6,0.9285714285714285,0.0003968253968253968 aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,0,0.6910233190806425,0.017844011512848347 -aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,2,0.6182840223353117,0.0340492747686748 -aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,6,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,7,0.7637626158259734,0.008839740160738534 -aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,8,0.7637626158259734,0.008839740160738534 -aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,9,0.7637626158259734,0.008839740160738534 -aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,2,0.6910233190806425,0.017844011512848347 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,3,0.836501912571304,0.004136737098676645 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,7,0.6182840223353117,0.0340492747686748 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,8,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,9,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,3,0.7637626158259734,0.008839740160738534 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,8,0.9092412093166348,0.0018276750354536814 aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968 -aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,6,0.9999999999999998,4.96031746031746e-05 -aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,8,0.9999999999999998,4.96031746031746e-05 -aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05 -aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,1,0.21428571428571427,0.5484126984126985 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,5,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,7,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111 aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,4,0.4999999999999999,0.10868055555555556 -aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,5,0.3571428571428571,0.27509920634920637 -aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,6,0.42857142857142855,0.17886904761904762 -aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,7,0.3571428571428571,0.27509920634920637 -aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,9,0.42857142857142855,0.17886904761904762 -aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,5,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,6,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,7,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,8,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 -aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,3,0.6182840223353117,0.0340492747686748 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,5,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,7,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,5,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,6,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,7,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,8,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,9,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556 aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762 -aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,5,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,6,0.5714285714285714,0.06101190476190476 -aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,7,0.6428571428571428,0.03115079365079365 -aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,8,0.8571428571428571,0.001736111111111111 -aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,9,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,5,0.9285714285714285,0.0003968253968253968 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,6,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,7,0.3571428571428571,0.27509920634920637 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,8,0.7857142857142856,0.005505952380952381 +aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,9,0.9999999999999998,4.96031746031746e-05