Spaces:
Running
Running
GLM-4.1V-thinking
Browse files
constants.py
CHANGED
|
@@ -156,6 +156,7 @@ MODEL_NAME_MAP = {
|
|
| 156 |
"InternVL3_78B": "InternVL3-78B",
|
| 157 |
"Ovis2_8B": "Ovis2-8B",
|
| 158 |
"Valley_Eagle_7B": "Valley-Eagle-7B",
|
|
|
|
| 159 |
}
|
| 160 |
|
| 161 |
DIMENSION_NAME_MAP = {
|
|
@@ -268,6 +269,7 @@ MODEL_URLS = {
|
|
| 268 |
"Seed1.5-VL": "https://github.com/ByteDance-Seed/Seed1.5-VL",
|
| 269 |
"Ovis2_8B": "https://huggingface.co/AIDC-AI/Ovis2-8B",
|
| 270 |
"Valley_Eagle_7B": "https://huggingface.co/bytedance-research/Valley-Eagle-7B",
|
|
|
|
| 271 |
}
|
| 272 |
|
| 273 |
# Define the base MODEL_GROUPS structure
|
|
@@ -326,6 +328,7 @@ BASE_MODEL_GROUPS = {
|
|
| 326 |
"InternVL3_14B",
|
| 327 |
"Ovis2_8B",
|
| 328 |
"Valley_Eagle_7B",
|
|
|
|
| 329 |
],
|
| 330 |
"Proprietary Flagship models": [
|
| 331 |
"Claude_3.5_new",
|
|
@@ -384,5 +387,6 @@ BASE_MODEL_GROUPS = {
|
|
| 384 |
"InternVL3_14B",
|
| 385 |
"Ovis2_8B",
|
| 386 |
"Valley_Eagle_7B",
|
|
|
|
| 387 |
],
|
| 388 |
}
|
|
|
|
| 156 |
"InternVL3_78B": "InternVL3-78B",
|
| 157 |
"Ovis2_8B": "Ovis2-8B",
|
| 158 |
"Valley_Eagle_7B": "Valley-Eagle-7B",
|
| 159 |
+
"GLM_4.1V_Thinking": "GLM-4.1V-Thinking"
|
| 160 |
}
|
| 161 |
|
| 162 |
DIMENSION_NAME_MAP = {
|
|
|
|
| 269 |
"Seed1.5-VL": "https://github.com/ByteDance-Seed/Seed1.5-VL",
|
| 270 |
"Ovis2_8B": "https://huggingface.co/AIDC-AI/Ovis2-8B",
|
| 271 |
"Valley_Eagle_7B": "https://huggingface.co/bytedance-research/Valley-Eagle-7B",
|
| 272 |
+
"GLM_4.1V_Thinking": "https://github.com/THUDM/GLM-4.1V-Thinking",
|
| 273 |
}
|
| 274 |
|
| 275 |
# Define the base MODEL_GROUPS structure
|
|
|
|
| 328 |
"InternVL3_14B",
|
| 329 |
"Ovis2_8B",
|
| 330 |
"Valley_Eagle_7B",
|
| 331 |
+
"GLM_4.1V_Thinking",
|
| 332 |
],
|
| 333 |
"Proprietary Flagship models": [
|
| 334 |
"Claude_3.5_new",
|
|
|
|
| 387 |
"InternVL3_14B",
|
| 388 |
"Ovis2_8B",
|
| 389 |
"Valley_Eagle_7B",
|
| 390 |
+
"GLM_4.1V_Thinking",
|
| 391 |
],
|
| 392 |
}
|
static/eval_results/Default/GLM_4.1V_Thinking/summary_and_keyword_stats.json
ADDED
|
@@ -0,0 +1,249 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_summary": {
|
| 3 |
+
"core": {
|
| 4 |
+
"num_eval_tasks": 440,
|
| 5 |
+
"num_eval_samples": 6531,
|
| 6 |
+
"macro_mean_score": 0.4486926203304986
|
| 7 |
+
},
|
| 8 |
+
"open": {
|
| 9 |
+
"num_eval_tasks": 65,
|
| 10 |
+
"num_eval_samples": 1158,
|
| 11 |
+
"macro_mean_score": 0.6108150206588362
|
| 12 |
+
},
|
| 13 |
+
"overall_score": 0.46955985997672023
|
| 14 |
+
},
|
| 15 |
+
"keyword_stats": {
|
| 16 |
+
"skills": {
|
| 17 |
+
"Text Recognition (OCR)": {
|
| 18 |
+
"count": 137,
|
| 19 |
+
"num_samples": 2215,
|
| 20 |
+
"tasks": [],
|
| 21 |
+
"average_score": 0.5172106384499557
|
| 22 |
+
},
|
| 23 |
+
"Language Understanding and Generation": {
|
| 24 |
+
"count": 154,
|
| 25 |
+
"num_samples": 2483,
|
| 26 |
+
"tasks": [],
|
| 27 |
+
"average_score": 0.5237662937025751
|
| 28 |
+
},
|
| 29 |
+
"Object Recognition and Classification": {
|
| 30 |
+
"count": 303,
|
| 31 |
+
"num_samples": 4712,
|
| 32 |
+
"tasks": [],
|
| 33 |
+
"average_score": 0.4953188385475589
|
| 34 |
+
},
|
| 35 |
+
"Scene and Event Understanding": {
|
| 36 |
+
"count": 154,
|
| 37 |
+
"num_samples": 2456,
|
| 38 |
+
"tasks": [],
|
| 39 |
+
"average_score": 0.5105629002516974
|
| 40 |
+
},
|
| 41 |
+
"Commonsense and Social Reasoning": {
|
| 42 |
+
"count": 51,
|
| 43 |
+
"num_samples": 850,
|
| 44 |
+
"tasks": [],
|
| 45 |
+
"average_score": 0.5560890513552442
|
| 46 |
+
},
|
| 47 |
+
"Mathematical and Logical Reasoning": {
|
| 48 |
+
"count": 109,
|
| 49 |
+
"num_samples": 1907,
|
| 50 |
+
"tasks": [],
|
| 51 |
+
"average_score": 0.45661405612330974
|
| 52 |
+
},
|
| 53 |
+
"Spatial and Temporal Reasoning": {
|
| 54 |
+
"count": 152,
|
| 55 |
+
"num_samples": 2430,
|
| 56 |
+
"tasks": [],
|
| 57 |
+
"average_score": 0.35774817817177057
|
| 58 |
+
},
|
| 59 |
+
"Planning and Decision Making": {
|
| 60 |
+
"count": 37,
|
| 61 |
+
"num_samples": 569,
|
| 62 |
+
"tasks": [],
|
| 63 |
+
"average_score": 0.16432465676580915
|
| 64 |
+
},
|
| 65 |
+
"Domain-Specific Knowledge and Skills": {
|
| 66 |
+
"count": 77,
|
| 67 |
+
"num_samples": 1383,
|
| 68 |
+
"tasks": [],
|
| 69 |
+
"average_score": 0.42985988743711107
|
| 70 |
+
},
|
| 71 |
+
"Ethical and Safety Reasoning": {
|
| 72 |
+
"count": 15,
|
| 73 |
+
"num_samples": 241,
|
| 74 |
+
"tasks": [],
|
| 75 |
+
"average_score": 0.5999448621553886
|
| 76 |
+
}
|
| 77 |
+
},
|
| 78 |
+
"input_format": {
|
| 79 |
+
"User Interface Screenshots": {
|
| 80 |
+
"count": 93,
|
| 81 |
+
"num_samples": 1487,
|
| 82 |
+
"tasks": [],
|
| 83 |
+
"average_score": 0.5318353838949659
|
| 84 |
+
},
|
| 85 |
+
"Videos": {
|
| 86 |
+
"count": 43,
|
| 87 |
+
"num_samples": 698,
|
| 88 |
+
"tasks": [],
|
| 89 |
+
"average_score": 0.42670039925394876
|
| 90 |
+
},
|
| 91 |
+
"Artistic and Creative Content": {
|
| 92 |
+
"count": 32,
|
| 93 |
+
"num_samples": 539,
|
| 94 |
+
"tasks": [],
|
| 95 |
+
"average_score": 0.4294089306737516
|
| 96 |
+
},
|
| 97 |
+
"Photographs": {
|
| 98 |
+
"count": 143,
|
| 99 |
+
"num_samples": 2239,
|
| 100 |
+
"tasks": [],
|
| 101 |
+
"average_score": 0.4897370296181892
|
| 102 |
+
},
|
| 103 |
+
"Diagrams and Data Visualizations": {
|
| 104 |
+
"count": 101,
|
| 105 |
+
"num_samples": 1715,
|
| 106 |
+
"tasks": [],
|
| 107 |
+
"average_score": 0.5037553614522623
|
| 108 |
+
},
|
| 109 |
+
"Text-Based Images and Documents": {
|
| 110 |
+
"count": 82,
|
| 111 |
+
"num_samples": 1286,
|
| 112 |
+
"tasks": [],
|
| 113 |
+
"average_score": 0.3644006697811522
|
| 114 |
+
},
|
| 115 |
+
"3D Models and Aerial Imagery": {
|
| 116 |
+
"count": 11,
|
| 117 |
+
"num_samples": 167,
|
| 118 |
+
"tasks": [],
|
| 119 |
+
"average_score": 0.4350267247634551
|
| 120 |
+
}
|
| 121 |
+
},
|
| 122 |
+
"output_format": {
|
| 123 |
+
"open_ended_output": {
|
| 124 |
+
"count": 80,
|
| 125 |
+
"num_samples": 1444,
|
| 126 |
+
"tasks": [],
|
| 127 |
+
"average_score": 0.5514161725392729
|
| 128 |
+
},
|
| 129 |
+
"contextual_formatted_text": {
|
| 130 |
+
"count": 98,
|
| 131 |
+
"num_samples": 1497,
|
| 132 |
+
"tasks": [],
|
| 133 |
+
"average_score": 0.44313348433053745
|
| 134 |
+
},
|
| 135 |
+
"structured_output": {
|
| 136 |
+
"count": 110,
|
| 137 |
+
"num_samples": 1710,
|
| 138 |
+
"tasks": [],
|
| 139 |
+
"average_score": 0.4067253221794801
|
| 140 |
+
},
|
| 141 |
+
"numerical_data": {
|
| 142 |
+
"count": 49,
|
| 143 |
+
"num_samples": 860,
|
| 144 |
+
"tasks": [],
|
| 145 |
+
"average_score": 0.5012861564098088
|
| 146 |
+
},
|
| 147 |
+
"multiple_choice": {
|
| 148 |
+
"count": 85,
|
| 149 |
+
"num_samples": 1347,
|
| 150 |
+
"tasks": [],
|
| 151 |
+
"average_score": 0.5010447004582862
|
| 152 |
+
},
|
| 153 |
+
"exact_text": {
|
| 154 |
+
"count": 83,
|
| 155 |
+
"num_samples": 1273,
|
| 156 |
+
"tasks": [],
|
| 157 |
+
"average_score": 0.4541656310594156
|
| 158 |
+
}
|
| 159 |
+
},
|
| 160 |
+
"input_num": {
|
| 161 |
+
"1-image": {
|
| 162 |
+
"count": 315,
|
| 163 |
+
"num_samples": 5207,
|
| 164 |
+
"tasks": [],
|
| 165 |
+
"average_score": 0.5009527875194596
|
| 166 |
+
},
|
| 167 |
+
"video": {
|
| 168 |
+
"count": 43,
|
| 169 |
+
"num_samples": 698,
|
| 170 |
+
"tasks": [],
|
| 171 |
+
"average_score": 0.42670039925394876
|
| 172 |
+
},
|
| 173 |
+
"4-5 images": {
|
| 174 |
+
"count": 34,
|
| 175 |
+
"num_samples": 520,
|
| 176 |
+
"tasks": [],
|
| 177 |
+
"average_score": 0.30537346326745196
|
| 178 |
+
},
|
| 179 |
+
"6-8 images": {
|
| 180 |
+
"count": 21,
|
| 181 |
+
"num_samples": 309,
|
| 182 |
+
"tasks": [],
|
| 183 |
+
"average_score": 0.41089380196523057
|
| 184 |
+
},
|
| 185 |
+
"2-3 images": {
|
| 186 |
+
"count": 51,
|
| 187 |
+
"num_samples": 802,
|
| 188 |
+
"tasks": [],
|
| 189 |
+
"average_score": 0.3990376069267054
|
| 190 |
+
},
|
| 191 |
+
"9-image or more": {
|
| 192 |
+
"count": 41,
|
| 193 |
+
"num_samples": 595,
|
| 194 |
+
"tasks": [],
|
| 195 |
+
"average_score": 0.5272463050260753
|
| 196 |
+
}
|
| 197 |
+
},
|
| 198 |
+
"app": {
|
| 199 |
+
"Information_Extraction": {
|
| 200 |
+
"count": 72,
|
| 201 |
+
"num_samples": 1099,
|
| 202 |
+
"tasks": [],
|
| 203 |
+
"average_score": 0.5840742162440538
|
| 204 |
+
},
|
| 205 |
+
"Knowledge": {
|
| 206 |
+
"count": 97,
|
| 207 |
+
"num_samples": 1602,
|
| 208 |
+
"tasks": [],
|
| 209 |
+
"average_score": 0.5107183342025416
|
| 210 |
+
},
|
| 211 |
+
"Perception": {
|
| 212 |
+
"count": 145,
|
| 213 |
+
"num_samples": 2305,
|
| 214 |
+
"tasks": [],
|
| 215 |
+
"average_score": 0.5237620974413176
|
| 216 |
+
},
|
| 217 |
+
"Planning": {
|
| 218 |
+
"count": 78,
|
| 219 |
+
"num_samples": 1222,
|
| 220 |
+
"tasks": [],
|
| 221 |
+
"average_score": 0.2653984706794158
|
| 222 |
+
},
|
| 223 |
+
"Science": {
|
| 224 |
+
"count": 29,
|
| 225 |
+
"num_samples": 574,
|
| 226 |
+
"tasks": [],
|
| 227 |
+
"average_score": 0.4503686780767413
|
| 228 |
+
},
|
| 229 |
+
"Metrics": {
|
| 230 |
+
"count": 20,
|
| 231 |
+
"num_samples": 309,
|
| 232 |
+
"tasks": [],
|
| 233 |
+
"average_score": 0.40954569202797303
|
| 234 |
+
},
|
| 235 |
+
"Coding": {
|
| 236 |
+
"count": 31,
|
| 237 |
+
"num_samples": 474,
|
| 238 |
+
"tasks": [],
|
| 239 |
+
"average_score": 0.350875350140056
|
| 240 |
+
},
|
| 241 |
+
"Mathematics": {
|
| 242 |
+
"count": 33,
|
| 243 |
+
"num_samples": 546,
|
| 244 |
+
"tasks": [],
|
| 245 |
+
"average_score": 0.507860033330701
|
| 246 |
+
}
|
| 247 |
+
}
|
| 248 |
+
}
|
| 249 |
+
}
|
static/eval_results/Default/GLM_4.1V_Thinking/task_results.json
ADDED
|
@@ -0,0 +1,3537 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"name": "GUI_Chat_Easy",
|
| 4 |
+
"score": 0.7230769230769231,
|
| 5 |
+
"eval_type": "llm",
|
| 6 |
+
"num_demo": 1,
|
| 7 |
+
"num_query": 26
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"name": "GUI_Chat_Hard",
|
| 11 |
+
"score": 0.5807692307692307,
|
| 12 |
+
"eval_type": "llm",
|
| 13 |
+
"num_demo": 1,
|
| 14 |
+
"num_query": 26
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"name": "activitynetqa",
|
| 18 |
+
"score": 0.5368421052631579,
|
| 19 |
+
"eval_type": "llm",
|
| 20 |
+
"num_demo": 1,
|
| 21 |
+
"num_query": 19
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"name": "art_explanation",
|
| 25 |
+
"score": 0.603448275862069,
|
| 26 |
+
"eval_type": "llm",
|
| 27 |
+
"num_demo": 1,
|
| 28 |
+
"num_query": 29
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"name": "ascii_art_30",
|
| 32 |
+
"score": 0.0,
|
| 33 |
+
"eval_type": "llm",
|
| 34 |
+
"num_demo": 1,
|
| 35 |
+
"num_query": 14
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"name": "bar_chart_interpretation",
|
| 39 |
+
"score": 0.5724137931034482,
|
| 40 |
+
"eval_type": "llm",
|
| 41 |
+
"num_demo": 1,
|
| 42 |
+
"num_query": 29
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"name": "bridge_strategies_advanced",
|
| 46 |
+
"score": 0.12142857142857143,
|
| 47 |
+
"eval_type": "llm",
|
| 48 |
+
"num_demo": 1,
|
| 49 |
+
"num_query": 14
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"name": "bridge_strategies_expert",
|
| 53 |
+
"score": 0.2571428571428572,
|
| 54 |
+
"eval_type": "llm",
|
| 55 |
+
"num_demo": 1,
|
| 56 |
+
"num_query": 14
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"name": "bridge_strategies_worldclass",
|
| 60 |
+
"score": 0.12142857142857144,
|
| 61 |
+
"eval_type": "llm",
|
| 62 |
+
"num_demo": 1,
|
| 63 |
+
"num_query": 14
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"name": "defeasible_reasoning",
|
| 67 |
+
"score": 0.8103448275862069,
|
| 68 |
+
"eval_type": "llm",
|
| 69 |
+
"num_demo": 1,
|
| 70 |
+
"num_query": 29
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"name": "doc_vqa",
|
| 74 |
+
"score": 0.7250000000000001,
|
| 75 |
+
"eval_type": "llm",
|
| 76 |
+
"num_demo": 1,
|
| 77 |
+
"num_query": 16
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"name": "docci_image_description_long",
|
| 81 |
+
"score": 0.8285714285714286,
|
| 82 |
+
"eval_type": "llm",
|
| 83 |
+
"num_demo": 1,
|
| 84 |
+
"num_query": 14
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"name": "electrocardiogram",
|
| 88 |
+
"score": 0.45714285714285713,
|
| 89 |
+
"eval_type": "llm",
|
| 90 |
+
"num_demo": 1,
|
| 91 |
+
"num_query": 14
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"name": "figurative_speech_explanation",
|
| 95 |
+
"score": 0.789655172413793,
|
| 96 |
+
"eval_type": "llm",
|
| 97 |
+
"num_demo": 1,
|
| 98 |
+
"num_query": 29
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"name": "funny_image_title",
|
| 102 |
+
"score": 0.5928571428571427,
|
| 103 |
+
"eval_type": "llm",
|
| 104 |
+
"num_demo": 1,
|
| 105 |
+
"num_query": 14
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"name": "funqa_unexpected_action_creative_video",
|
| 109 |
+
"score": 0.4133333333333334,
|
| 110 |
+
"eval_type": "llm",
|
| 111 |
+
"num_demo": 1,
|
| 112 |
+
"num_query": 15
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"name": "funqa_unexpected_action_humor_video",
|
| 116 |
+
"score": 0.37333333333333335,
|
| 117 |
+
"eval_type": "llm",
|
| 118 |
+
"num_demo": 1,
|
| 119 |
+
"num_query": 15
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"name": "funqa_unexpected_action_magic_video",
|
| 123 |
+
"score": 0.6,
|
| 124 |
+
"eval_type": "llm",
|
| 125 |
+
"num_demo": 1,
|
| 126 |
+
"num_query": 15
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"name": "generated_video_artifacts",
|
| 130 |
+
"score": 0.43125,
|
| 131 |
+
"eval_type": "llm",
|
| 132 |
+
"num_demo": 1,
|
| 133 |
+
"num_query": 16
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"name": "graph_interpretation",
|
| 137 |
+
"score": 0.8379310344827585,
|
| 138 |
+
"eval_type": "llm",
|
| 139 |
+
"num_demo": 1,
|
| 140 |
+
"num_query": 29
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"name": "guess_image_generation_prompt",
|
| 144 |
+
"score": 0.836842105263158,
|
| 145 |
+
"eval_type": "llm",
|
| 146 |
+
"num_demo": 1,
|
| 147 |
+
"num_query": 19
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"name": "humor_explanation",
|
| 151 |
+
"score": 0.6533333333333334,
|
| 152 |
+
"eval_type": "llm",
|
| 153 |
+
"num_demo": 1,
|
| 154 |
+
"num_query": 15
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"name": "image_captioning_with_additional_requirements",
|
| 158 |
+
"score": 0.9000000000000001,
|
| 159 |
+
"eval_type": "llm",
|
| 160 |
+
"num_demo": 1,
|
| 161 |
+
"num_query": 14
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"name": "image_humor_understanding",
|
| 165 |
+
"score": 0.8172413793103449,
|
| 166 |
+
"eval_type": "llm",
|
| 167 |
+
"num_demo": 1,
|
| 168 |
+
"num_query": 29
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"name": "iq_test_open_ended",
|
| 172 |
+
"score": 0.7586206896551724,
|
| 173 |
+
"eval_type": "llm",
|
| 174 |
+
"num_demo": 1,
|
| 175 |
+
"num_query": 29
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"name": "meme_explain",
|
| 179 |
+
"score": 0.7857142857142857,
|
| 180 |
+
"eval_type": "llm",
|
| 181 |
+
"num_demo": 1,
|
| 182 |
+
"num_query": 14
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"name": "multi_lingual_Ruozhiba_expalnation_Arabic",
|
| 186 |
+
"score": 0.5857142857142856,
|
| 187 |
+
"eval_type": "llm",
|
| 188 |
+
"num_demo": 1,
|
| 189 |
+
"num_query": 14
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"name": "multi_lingual_Ruozhiba_expalnation_English",
|
| 193 |
+
"score": 0.6857142857142858,
|
| 194 |
+
"eval_type": "llm",
|
| 195 |
+
"num_demo": 1,
|
| 196 |
+
"num_query": 14
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"name": "multi_lingual_Ruozhiba_expalnation_French",
|
| 200 |
+
"score": 0.6428571428571427,
|
| 201 |
+
"eval_type": "llm",
|
| 202 |
+
"num_demo": 1,
|
| 203 |
+
"num_query": 14
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"name": "multi_lingual_Ruozhiba_expalnation_Japanese",
|
| 207 |
+
"score": 0.6,
|
| 208 |
+
"eval_type": "llm",
|
| 209 |
+
"num_demo": 1,
|
| 210 |
+
"num_query": 14
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"name": "multi_lingual_Ruozhiba_expalnation_Russian",
|
| 214 |
+
"score": 0.5999999999999999,
|
| 215 |
+
"eval_type": "llm",
|
| 216 |
+
"num_demo": 1,
|
| 217 |
+
"num_query": 14
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"name": "multi_lingual_Ruozhiba_expalnation_Spanish",
|
| 221 |
+
"score": 0.6428571428571427,
|
| 222 |
+
"eval_type": "llm",
|
| 223 |
+
"num_demo": 1,
|
| 224 |
+
"num_query": 14
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"name": "multi_lingual_manual_explanation_scooter_Arabic",
|
| 228 |
+
"score": 0.37142857142857144,
|
| 229 |
+
"eval_type": "llm",
|
| 230 |
+
"num_demo": 0,
|
| 231 |
+
"num_query": 14
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"name": "multi_lingual_manual_explanation_scooter_Chinese",
|
| 235 |
+
"score": 0.5071428571428572,
|
| 236 |
+
"eval_type": "llm",
|
| 237 |
+
"num_demo": 0,
|
| 238 |
+
"num_query": 14
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"name": "multi_lingual_manual_explanation_scooter_French",
|
| 242 |
+
"score": 0.45714285714285713,
|
| 243 |
+
"eval_type": "llm",
|
| 244 |
+
"num_demo": 0,
|
| 245 |
+
"num_query": 14
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"name": "multi_lingual_manual_explanation_scooter_Russian",
|
| 249 |
+
"score": 0.5,
|
| 250 |
+
"eval_type": "llm",
|
| 251 |
+
"num_demo": 0,
|
| 252 |
+
"num_query": 14
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"name": "multi_lingual_manual_explanation_scooter_Spanish",
|
| 256 |
+
"score": 0.4928571428571429,
|
| 257 |
+
"eval_type": "llm",
|
| 258 |
+
"num_demo": 0,
|
| 259 |
+
"num_query": 14
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"name": "nextqa_oe",
|
| 263 |
+
"score": 0.6,
|
| 264 |
+
"eval_type": "llm",
|
| 265 |
+
"num_demo": 1,
|
| 266 |
+
"num_query": 19
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"name": "ocr_open_ended_qa",
|
| 270 |
+
"score": 0.8689655172413792,
|
| 271 |
+
"eval_type": "llm",
|
| 272 |
+
"num_demo": 1,
|
| 273 |
+
"num_query": 29
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"name": "paper_review_writing",
|
| 277 |
+
"score": 0.6533333333333332,
|
| 278 |
+
"eval_type": "llm",
|
| 279 |
+
"num_demo": 1,
|
| 280 |
+
"num_query": 15
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"name": "red_teaming_captcha",
|
| 284 |
+
"score": 0.10000000000000003,
|
| 285 |
+
"eval_type": "llm",
|
| 286 |
+
"num_demo": 1,
|
| 287 |
+
"num_query": 19
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"name": "red_teaming_celebrity",
|
| 291 |
+
"score": 0.6500000000000001,
|
| 292 |
+
"eval_type": "llm",
|
| 293 |
+
"num_demo": 0,
|
| 294 |
+
"num_query": 20
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"name": "red_teaming_jailbreak",
|
| 298 |
+
"score": 0.51,
|
| 299 |
+
"eval_type": "llm",
|
| 300 |
+
"num_demo": 0,
|
| 301 |
+
"num_query": 20
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"name": "red_teaming_politics",
|
| 305 |
+
"score": 0.74,
|
| 306 |
+
"eval_type": "llm",
|
| 307 |
+
"num_demo": 0,
|
| 308 |
+
"num_query": 20
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"name": "red_teaming_racial",
|
| 312 |
+
"score": 0.78,
|
| 313 |
+
"eval_type": "llm",
|
| 314 |
+
"num_demo": 0,
|
| 315 |
+
"num_query": 20
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"name": "red_teaming_visual_order_A",
|
| 319 |
+
"score": 0.9,
|
| 320 |
+
"eval_type": "llm",
|
| 321 |
+
"num_demo": 1,
|
| 322 |
+
"num_query": 19
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"name": "red_teaming_visual_order_B",
|
| 326 |
+
"score": 0.8894736842105264,
|
| 327 |
+
"eval_type": "llm",
|
| 328 |
+
"num_demo": 1,
|
| 329 |
+
"num_query": 19
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"name": "red_teaming_visualmisleading",
|
| 333 |
+
"score": 0.8263157894736844,
|
| 334 |
+
"eval_type": "llm",
|
| 335 |
+
"num_demo": 1,
|
| 336 |
+
"num_query": 19
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"name": "sceneqa_scene_transition_video",
|
| 340 |
+
"score": 0.4214285714285714,
|
| 341 |
+
"eval_type": "llm",
|
| 342 |
+
"num_demo": 1,
|
| 343 |
+
"num_query": 14
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"name": "scibench_w_solution_open_ended",
|
| 347 |
+
"score": 0.41,
|
| 348 |
+
"eval_type": "llm",
|
| 349 |
+
"num_demo": 1,
|
| 350 |
+
"num_query": 25
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"name": "science_figure_explanation",
|
| 354 |
+
"score": 0.8275862068965518,
|
| 355 |
+
"eval_type": "llm",
|
| 356 |
+
"num_demo": 1,
|
| 357 |
+
"num_query": 29
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"name": "table2latex_complex",
|
| 361 |
+
"score": 0.6777777777777777,
|
| 362 |
+
"eval_type": "llm",
|
| 363 |
+
"num_demo": 1,
|
| 364 |
+
"num_query": 9
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"name": "table_understanding_fetaqa",
|
| 368 |
+
"score": 0.6357142857142859,
|
| 369 |
+
"eval_type": "llm",
|
| 370 |
+
"num_demo": 1,
|
| 371 |
+
"num_query": 14
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"name": "traffic_accident_analysis",
|
| 375 |
+
"score": 0.7357142857142858,
|
| 376 |
+
"eval_type": "llm",
|
| 377 |
+
"num_demo": 1,
|
| 378 |
+
"num_query": 14
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"name": "tweets_captioning",
|
| 382 |
+
"score": 0.5428571428571428,
|
| 383 |
+
"eval_type": "llm",
|
| 384 |
+
"num_demo": 1,
|
| 385 |
+
"num_query": 14
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"name": "unusual_images",
|
| 389 |
+
"score": 0.8172413793103449,
|
| 390 |
+
"eval_type": "llm",
|
| 391 |
+
"num_demo": 1,
|
| 392 |
+
"num_query": 29
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"name": "vibe_eval_phrase",
|
| 396 |
+
"score": 0.7000000000000001,
|
| 397 |
+
"eval_type": "llm",
|
| 398 |
+
"num_demo": 1,
|
| 399 |
+
"num_query": 14
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"name": "video2notes",
|
| 403 |
+
"score": 0.5714285714285714,
|
| 404 |
+
"eval_type": "llm",
|
| 405 |
+
"num_demo": 1,
|
| 406 |
+
"num_query": 14
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"name": "video_content_follow_up",
|
| 410 |
+
"score": 0.7928571428571429,
|
| 411 |
+
"eval_type": "llm",
|
| 412 |
+
"num_demo": 1,
|
| 413 |
+
"num_query": 14
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"name": "video_detail_description",
|
| 417 |
+
"score": 0.6578947368421053,
|
| 418 |
+
"eval_type": "llm",
|
| 419 |
+
"num_demo": 1,
|
| 420 |
+
"num_query": 19
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"name": "video_qa",
|
| 424 |
+
"score": 0.7928571428571428,
|
| 425 |
+
"eval_type": "llm",
|
| 426 |
+
"num_demo": 1,
|
| 427 |
+
"num_query": 14
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"name": "video_short_title",
|
| 431 |
+
"score": 0.6142857142857142,
|
| 432 |
+
"eval_type": "llm",
|
| 433 |
+
"num_demo": 1,
|
| 434 |
+
"num_query": 14
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"name": "video_summary",
|
| 438 |
+
"score": 0.6285714285714284,
|
| 439 |
+
"eval_type": "llm",
|
| 440 |
+
"num_demo": 1,
|
| 441 |
+
"num_query": 14
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"name": "visualization_with_code",
|
| 445 |
+
"score": 0.5785714285714286,
|
| 446 |
+
"eval_type": "llm",
|
| 447 |
+
"num_demo": 1,
|
| 448 |
+
"num_query": 14
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"name": "wikihow_complex_task_completion",
|
| 452 |
+
"score": 0.5666666666666667,
|
| 453 |
+
"eval_type": "llm",
|
| 454 |
+
"num_demo": 1,
|
| 455 |
+
"num_query": 9
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"name": "2d_image_jigsaw_puzzle_easy",
|
| 459 |
+
"score": 0.1619047619047619,
|
| 460 |
+
"eval_type": "rule",
|
| 461 |
+
"num_demo": 1,
|
| 462 |
+
"num_query": 14
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"name": "3d_fragments_understanding",
|
| 466 |
+
"score": 0.14285714285714285,
|
| 467 |
+
"eval_type": "rule",
|
| 468 |
+
"num_demo": 1,
|
| 469 |
+
"num_query": 14
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"name": "3d_indoor_scene_text_bbox_prediction",
|
| 473 |
+
"score": 0.2743696026501071,
|
| 474 |
+
"eval_type": "rule",
|
| 475 |
+
"num_demo": 0,
|
| 476 |
+
"num_query": 14
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"name": "3d_indoor_scene_text_bbox_selection",
|
| 480 |
+
"score": 0.7142857142857143,
|
| 481 |
+
"eval_type": "rule",
|
| 482 |
+
"num_demo": 0,
|
| 483 |
+
"num_query": 14
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"name": "Ad_count_detection",
|
| 487 |
+
"score": 0.6071428571428571,
|
| 488 |
+
"eval_type": "rule",
|
| 489 |
+
"num_demo": 1,
|
| 490 |
+
"num_query": 14
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"name": "GUI_Act_Mobile_swipe",
|
| 494 |
+
"score": 0.5002159519380676,
|
| 495 |
+
"eval_type": "rule",
|
| 496 |
+
"num_demo": 1,
|
| 497 |
+
"num_query": 13
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"name": "GUI_Act_Mobile_tap",
|
| 501 |
+
"score": 0.21428571428571427,
|
| 502 |
+
"eval_type": "rule",
|
| 503 |
+
"num_demo": 1,
|
| 504 |
+
"num_query": 14
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"name": "GUI_Act_Web_Multi",
|
| 508 |
+
"score": 0.42857142857142855,
|
| 509 |
+
"eval_type": "rule",
|
| 510 |
+
"num_demo": 1,
|
| 511 |
+
"num_query": 14
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"name": "GUI_Act_Web_Single",
|
| 515 |
+
"score": 0.0,
|
| 516 |
+
"eval_type": "rule",
|
| 517 |
+
"num_demo": 1,
|
| 518 |
+
"num_query": 14
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"name": "IAM_line_ocr_and_locate",
|
| 522 |
+
"score": 0.5600541516009605,
|
| 523 |
+
"eval_type": "rule",
|
| 524 |
+
"num_demo": 1,
|
| 525 |
+
"num_query": 14
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"name": "MMMU_physics_chemistry_selected",
|
| 529 |
+
"score": 0.7142857142857143,
|
| 530 |
+
"eval_type": "rule",
|
| 531 |
+
"num_demo": 1,
|
| 532 |
+
"num_query": 14
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"name": "MMMU_pro_exam_screenshot",
|
| 536 |
+
"score": 0.48484848484848486,
|
| 537 |
+
"eval_type": "rule",
|
| 538 |
+
"num_demo": 1,
|
| 539 |
+
"num_query": 99
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"name": "MMSoc_HatefulMemes",
|
| 543 |
+
"score": 0.7142857142857143,
|
| 544 |
+
"eval_type": "rule",
|
| 545 |
+
"num_demo": 1,
|
| 546 |
+
"num_query": 14
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"name": "MMSoc_Memotion",
|
| 550 |
+
"score": 0.611764705882353,
|
| 551 |
+
"eval_type": "rule",
|
| 552 |
+
"num_demo": 1,
|
| 553 |
+
"num_query": 17
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"name": "MMSoc_Misinformation_GossipCop",
|
| 557 |
+
"score": 0.7142857142857143,
|
| 558 |
+
"eval_type": "rule",
|
| 559 |
+
"num_demo": 1,
|
| 560 |
+
"num_query": 14
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"name": "MMSoc_Misinformation_PolitiFact",
|
| 564 |
+
"score": 0.7857142857142857,
|
| 565 |
+
"eval_type": "rule",
|
| 566 |
+
"num_demo": 1,
|
| 567 |
+
"num_query": 14
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"name": "TRANCE_physics_reasoning_basic",
|
| 571 |
+
"score": 0.8823529411764706,
|
| 572 |
+
"eval_type": "rule",
|
| 573 |
+
"num_demo": 1,
|
| 574 |
+
"num_query": 17
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"name": "TRANCE_physics_reasoning_event",
|
| 578 |
+
"score": 0.21428571428571427,
|
| 579 |
+
"eval_type": "rule",
|
| 580 |
+
"num_demo": 1,
|
| 581 |
+
"num_query": 14
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"name": "TRANCE_physics_reasoning_view",
|
| 585 |
+
"score": 0.07142857142857142,
|
| 586 |
+
"eval_type": "rule",
|
| 587 |
+
"num_demo": 1,
|
| 588 |
+
"num_query": 14
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"name": "TV_show_info_parsing",
|
| 592 |
+
"score": 0.753968253968254,
|
| 593 |
+
"eval_type": "rule",
|
| 594 |
+
"num_demo": 1,
|
| 595 |
+
"num_query": 14
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"name": "action_sequence_understanding",
|
| 599 |
+
"score": 0.5,
|
| 600 |
+
"eval_type": "rule",
|
| 601 |
+
"num_demo": 1,
|
| 602 |
+
"num_query": 14
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"name": "actor_recognition_in_Movie",
|
| 606 |
+
"score": 0.5,
|
| 607 |
+
"eval_type": "rule",
|
| 608 |
+
"num_demo": 1,
|
| 609 |
+
"num_query": 14
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"name": "adapted_cvbench_count",
|
| 613 |
+
"score": 0.7142857142857143,
|
| 614 |
+
"eval_type": "rule",
|
| 615 |
+
"num_demo": 1,
|
| 616 |
+
"num_query": 14
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"name": "adapted_cvbench_depth",
|
| 620 |
+
"score": 0.8571428571428571,
|
| 621 |
+
"eval_type": "rule",
|
| 622 |
+
"num_demo": 1,
|
| 623 |
+
"num_query": 14
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"name": "adapted_cvbench_distance",
|
| 627 |
+
"score": 0.6428571428571429,
|
| 628 |
+
"eval_type": "rule",
|
| 629 |
+
"num_demo": 1,
|
| 630 |
+
"num_query": 14
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"name": "adapted_cvbench_relation",
|
| 634 |
+
"score": 0.2857142857142857,
|
| 635 |
+
"eval_type": "rule",
|
| 636 |
+
"num_demo": 1,
|
| 637 |
+
"num_query": 14
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"name": "algebra",
|
| 641 |
+
"score": 0.2857142857142857,
|
| 642 |
+
"eval_type": "rule",
|
| 643 |
+
"num_demo": 1,
|
| 644 |
+
"num_query": 14
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"name": "ancient_map_understanding",
|
| 648 |
+
"score": 0.9285714285714286,
|
| 649 |
+
"eval_type": "rule",
|
| 650 |
+
"num_demo": 1,
|
| 651 |
+
"num_query": 14
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"name": "animal_pose_estimation",
|
| 655 |
+
"score": 0.3256744538032678,
|
| 656 |
+
"eval_type": "rule",
|
| 657 |
+
"num_demo": 1,
|
| 658 |
+
"num_query": 14
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"name": "annoying_word_search",
|
| 662 |
+
"score": 0.0,
|
| 663 |
+
"eval_type": "rule",
|
| 664 |
+
"num_demo": 1,
|
| 665 |
+
"num_query": 14
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"name": "app_interactive_operations_alipay",
|
| 669 |
+
"score": 0.6470588235294118,
|
| 670 |
+
"eval_type": "rule",
|
| 671 |
+
"num_demo": 0,
|
| 672 |
+
"num_query": 17
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"name": "app_interactive_operations_amazon",
|
| 676 |
+
"score": 0.6428571428571429,
|
| 677 |
+
"eval_type": "rule",
|
| 678 |
+
"num_demo": 0,
|
| 679 |
+
"num_query": 14
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"name": "app_interactive_operations_excel",
|
| 683 |
+
"score": 0.42857142857142855,
|
| 684 |
+
"eval_type": "rule",
|
| 685 |
+
"num_demo": 0,
|
| 686 |
+
"num_query": 14
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"name": "app_interactive_operations_instagram",
|
| 690 |
+
"score": 0.7142857142857143,
|
| 691 |
+
"eval_type": "rule",
|
| 692 |
+
"num_demo": 0,
|
| 693 |
+
"num_query": 14
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"name": "app_interactive_operations_iphone_settings",
|
| 697 |
+
"score": 0.7857142857142857,
|
| 698 |
+
"eval_type": "rule",
|
| 699 |
+
"num_demo": 0,
|
| 700 |
+
"num_query": 14
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"name": "app_interactive_operations_leetcode",
|
| 704 |
+
"score": 0.6428571428571429,
|
| 705 |
+
"eval_type": "rule",
|
| 706 |
+
"num_demo": 0,
|
| 707 |
+
"num_query": 14
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"name": "app_interactive_operations_notes",
|
| 711 |
+
"score": 0.42857142857142855,
|
| 712 |
+
"eval_type": "rule",
|
| 713 |
+
"num_demo": 0,
|
| 714 |
+
"num_query": 14
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"name": "app_interactive_operations_ppt",
|
| 718 |
+
"score": 0.7142857142857143,
|
| 719 |
+
"eval_type": "rule",
|
| 720 |
+
"num_demo": 0,
|
| 721 |
+
"num_query": 14
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"name": "app_interactive_operations_tiktok",
|
| 725 |
+
"score": 0.7142857142857143,
|
| 726 |
+
"eval_type": "rule",
|
| 727 |
+
"num_demo": 0,
|
| 728 |
+
"num_query": 14
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"name": "app_interactive_operations_twitter",
|
| 732 |
+
"score": 0.7142857142857143,
|
| 733 |
+
"eval_type": "rule",
|
| 734 |
+
"num_demo": 0,
|
| 735 |
+
"num_query": 14
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"name": "app_interactive_operations_word",
|
| 739 |
+
"score": 0.35714285714285715,
|
| 740 |
+
"eval_type": "rule",
|
| 741 |
+
"num_demo": 0,
|
| 742 |
+
"num_query": 14
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"name": "app_interactive_operations_youtube",
|
| 746 |
+
"score": 0.8571428571428571,
|
| 747 |
+
"eval_type": "rule",
|
| 748 |
+
"num_demo": 0,
|
| 749 |
+
"num_query": 14
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"name": "app_interactive_operations_zoom",
|
| 753 |
+
"score": 0.4666666666666667,
|
| 754 |
+
"eval_type": "rule",
|
| 755 |
+
"num_demo": 0,
|
| 756 |
+
"num_query": 15
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"name": "app_layout_understanding_alipay",
|
| 760 |
+
"score": 0.6470588235294118,
|
| 761 |
+
"eval_type": "rule",
|
| 762 |
+
"num_demo": 1,
|
| 763 |
+
"num_query": 17
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"name": "app_layout_understanding_amazon",
|
| 767 |
+
"score": 0.35714285714285715,
|
| 768 |
+
"eval_type": "rule",
|
| 769 |
+
"num_demo": 1,
|
| 770 |
+
"num_query": 14
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"name": "app_layout_understanding_excel",
|
| 774 |
+
"score": 0.42857142857142855,
|
| 775 |
+
"eval_type": "rule",
|
| 776 |
+
"num_demo": 1,
|
| 777 |
+
"num_query": 14
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"name": "app_layout_understanding_instagram",
|
| 781 |
+
"score": 0.7857142857142857,
|
| 782 |
+
"eval_type": "rule",
|
| 783 |
+
"num_demo": 1,
|
| 784 |
+
"num_query": 14
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"name": "app_layout_understanding_iphone_settings",
|
| 788 |
+
"score": 0.7857142857142857,
|
| 789 |
+
"eval_type": "rule",
|
| 790 |
+
"num_demo": 1,
|
| 791 |
+
"num_query": 14
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"name": "app_layout_understanding_leetcode",
|
| 795 |
+
"score": 0.2857142857142857,
|
| 796 |
+
"eval_type": "rule",
|
| 797 |
+
"num_demo": 1,
|
| 798 |
+
"num_query": 14
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"name": "app_layout_understanding_notes",
|
| 802 |
+
"score": 0.42857142857142855,
|
| 803 |
+
"eval_type": "rule",
|
| 804 |
+
"num_demo": 1,
|
| 805 |
+
"num_query": 14
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"name": "app_layout_understanding_ppt",
|
| 809 |
+
"score": 0.6428571428571429,
|
| 810 |
+
"eval_type": "rule",
|
| 811 |
+
"num_demo": 1,
|
| 812 |
+
"num_query": 14
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"name": "app_layout_understanding_tiktok",
|
| 816 |
+
"score": 0.5714285714285714,
|
| 817 |
+
"eval_type": "rule",
|
| 818 |
+
"num_demo": 1,
|
| 819 |
+
"num_query": 14
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"name": "app_layout_understanding_twitter",
|
| 823 |
+
"score": 0.7142857142857143,
|
| 824 |
+
"eval_type": "rule",
|
| 825 |
+
"num_demo": 1,
|
| 826 |
+
"num_query": 14
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"name": "app_layout_understanding_word",
|
| 830 |
+
"score": 0.6428571428571429,
|
| 831 |
+
"eval_type": "rule",
|
| 832 |
+
"num_demo": 1,
|
| 833 |
+
"num_query": 14
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"name": "app_layout_understanding_youtube",
|
| 837 |
+
"score": 0.7142857142857143,
|
| 838 |
+
"eval_type": "rule",
|
| 839 |
+
"num_demo": 1,
|
| 840 |
+
"num_query": 14
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"name": "app_layout_understanding_zoom",
|
| 844 |
+
"score": 0.6,
|
| 845 |
+
"eval_type": "rule",
|
| 846 |
+
"num_demo": 1,
|
| 847 |
+
"num_query": 15
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"name": "arc_agi",
|
| 851 |
+
"score": 0.0,
|
| 852 |
+
"eval_type": "rule",
|
| 853 |
+
"num_demo": 1,
|
| 854 |
+
"num_query": 14
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"name": "arxiv_vqa",
|
| 858 |
+
"score": 0.7857142857142857,
|
| 859 |
+
"eval_type": "rule",
|
| 860 |
+
"num_demo": 1,
|
| 861 |
+
"num_query": 14
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"name": "ascii_art_understanding",
|
| 865 |
+
"score": 0.5,
|
| 866 |
+
"eval_type": "rule",
|
| 867 |
+
"num_demo": 1,
|
| 868 |
+
"num_query": 14
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"name": "autonomous_driving_scene_analysis",
|
| 872 |
+
"score": 0.9285714285714286,
|
| 873 |
+
"eval_type": "rule",
|
| 874 |
+
"num_demo": 1,
|
| 875 |
+
"num_query": 14
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"name": "autorater_3d_model_texturing",
|
| 879 |
+
"score": 0.6428571428571429,
|
| 880 |
+
"eval_type": "rule",
|
| 881 |
+
"num_demo": 1,
|
| 882 |
+
"num_query": 14
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"name": "autorater_aesthetics",
|
| 886 |
+
"score": 0.6428571428571429,
|
| 887 |
+
"eval_type": "rule",
|
| 888 |
+
"num_demo": 1,
|
| 889 |
+
"num_query": 14
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"name": "autorater_artifact",
|
| 893 |
+
"score": 0.21428571428571427,
|
| 894 |
+
"eval_type": "rule",
|
| 895 |
+
"num_demo": 1,
|
| 896 |
+
"num_query": 14
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"name": "autorater_artifact_reason",
|
| 900 |
+
"score": 0.3333333333333333,
|
| 901 |
+
"eval_type": "rule",
|
| 902 |
+
"num_demo": 0,
|
| 903 |
+
"num_query": 15
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"name": "autorater_control",
|
| 907 |
+
"score": 0.7857142857142857,
|
| 908 |
+
"eval_type": "rule",
|
| 909 |
+
"num_demo": 1,
|
| 910 |
+
"num_query": 14
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"name": "autorater_mask",
|
| 914 |
+
"score": 0.2857142857142857,
|
| 915 |
+
"eval_type": "rule",
|
| 916 |
+
"num_demo": 1,
|
| 917 |
+
"num_query": 14
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"name": "autorater_motion_guided_editing",
|
| 921 |
+
"score": 0.14285714285714285,
|
| 922 |
+
"eval_type": "rule",
|
| 923 |
+
"num_demo": 1,
|
| 924 |
+
"num_query": 14
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"name": "autorater_semantics",
|
| 928 |
+
"score": 0.7857142857142857,
|
| 929 |
+
"eval_type": "rule",
|
| 930 |
+
"num_demo": 1,
|
| 931 |
+
"num_query": 14
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"name": "autorater_subject",
|
| 935 |
+
"score": 0.5714285714285714,
|
| 936 |
+
"eval_type": "rule",
|
| 937 |
+
"num_demo": 1,
|
| 938 |
+
"num_query": 14
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"name": "autorater_unmask",
|
| 942 |
+
"score": 0.21428571428571427,
|
| 943 |
+
"eval_type": "rule",
|
| 944 |
+
"num_demo": 1,
|
| 945 |
+
"num_query": 14
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"name": "av_human_multiview_counting",
|
| 949 |
+
"score": 0.13333333333333333,
|
| 950 |
+
"eval_type": "rule",
|
| 951 |
+
"num_demo": 1,
|
| 952 |
+
"num_query": 15
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"name": "av_multicamera_tracking_predict_bbox",
|
| 956 |
+
"score": 0.01836734693877553,
|
| 957 |
+
"eval_type": "rule",
|
| 958 |
+
"num_demo": 1,
|
| 959 |
+
"num_query": 14
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"name": "av_vehicle_multiview_counting",
|
| 963 |
+
"score": 0.13333333333333333,
|
| 964 |
+
"eval_type": "rule",
|
| 965 |
+
"num_demo": 1,
|
| 966 |
+
"num_query": 15
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"name": "av_view_identification",
|
| 970 |
+
"score": 0.17777777777777776,
|
| 971 |
+
"eval_type": "rule",
|
| 972 |
+
"num_demo": 1,
|
| 973 |
+
"num_query": 15
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"name": "average_humidity_estimate_plot",
|
| 977 |
+
"score": 0.724,
|
| 978 |
+
"eval_type": "rule",
|
| 979 |
+
"num_demo": 1,
|
| 980 |
+
"num_query": 15
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"name": "background_change",
|
| 984 |
+
"score": 0.7142857142857143,
|
| 985 |
+
"eval_type": "rule",
|
| 986 |
+
"num_demo": 1,
|
| 987 |
+
"num_query": 14
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"name": "ball_cup_swap_3",
|
| 991 |
+
"score": 0.21428571428571427,
|
| 992 |
+
"eval_type": "rule",
|
| 993 |
+
"num_demo": 1,
|
| 994 |
+
"num_query": 14
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"name": "biology_exams_v",
|
| 998 |
+
"score": 0.42857142857142855,
|
| 999 |
+
"eval_type": "rule",
|
| 1000 |
+
"num_demo": 1,
|
| 1001 |
+
"num_query": 14
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"name": "bongard_problem",
|
| 1005 |
+
"score": 0.23684210526315788,
|
| 1006 |
+
"eval_type": "rule",
|
| 1007 |
+
"num_demo": 1,
|
| 1008 |
+
"num_query": 19
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"name": "booking_web_rating",
|
| 1012 |
+
"score": 1.0,
|
| 1013 |
+
"eval_type": "rule",
|
| 1014 |
+
"num_demo": 0,
|
| 1015 |
+
"num_query": 14
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"name": "booking_web_recommendation",
|
| 1019 |
+
"score": 0.8092403628117913,
|
| 1020 |
+
"eval_type": "rule",
|
| 1021 |
+
"num_demo": 0,
|
| 1022 |
+
"num_query": 14
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"name": "brand_logo_recognition_and_elaboration",
|
| 1026 |
+
"score": 0.68,
|
| 1027 |
+
"eval_type": "rule",
|
| 1028 |
+
"num_demo": 1,
|
| 1029 |
+
"num_query": 25
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"name": "calendar_schedule_suggestion",
|
| 1033 |
+
"score": 0.2857142857142857,
|
| 1034 |
+
"eval_type": "rule",
|
| 1035 |
+
"num_demo": 0,
|
| 1036 |
+
"num_query": 14
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"name": "cam_traj_to_video_selection",
|
| 1040 |
+
"score": 0.42857142857142855,
|
| 1041 |
+
"eval_type": "rule",
|
| 1042 |
+
"num_demo": 1,
|
| 1043 |
+
"num_query": 14
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"name": "character_recognition_in_TV_shows",
|
| 1047 |
+
"score": 0.42857142857142855,
|
| 1048 |
+
"eval_type": "rule",
|
| 1049 |
+
"num_demo": 1,
|
| 1050 |
+
"num_query": 14
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"name": "chart_vqa",
|
| 1054 |
+
"score": 0.7142857142857143,
|
| 1055 |
+
"eval_type": "rule",
|
| 1056 |
+
"num_demo": 1,
|
| 1057 |
+
"num_query": 14
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"name": "cheapest_flight_identification",
|
| 1061 |
+
"score": 0.35714285714285715,
|
| 1062 |
+
"eval_type": "rule",
|
| 1063 |
+
"num_demo": 1,
|
| 1064 |
+
"num_query": 14
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"name": "chemistry_exams_v",
|
| 1068 |
+
"score": 0.14285714285714285,
|
| 1069 |
+
"eval_type": "rule",
|
| 1070 |
+
"num_demo": 1,
|
| 1071 |
+
"num_query": 14
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"name": "chess_find_legal_moves",
|
| 1075 |
+
"score": 0.01263043897090046,
|
| 1076 |
+
"eval_type": "rule",
|
| 1077 |
+
"num_demo": 1,
|
| 1078 |
+
"num_query": 14
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"name": "chess_puzzle_single_step",
|
| 1082 |
+
"score": 0.0,
|
| 1083 |
+
"eval_type": "rule",
|
| 1084 |
+
"num_demo": 1,
|
| 1085 |
+
"num_query": 15
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"name": "chess_puzzles_checkmate",
|
| 1089 |
+
"score": 0.0,
|
| 1090 |
+
"eval_type": "rule",
|
| 1091 |
+
"num_demo": 1,
|
| 1092 |
+
"num_query": 14
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"name": "chess_puzzles_crushing",
|
| 1096 |
+
"score": 0.0,
|
| 1097 |
+
"eval_type": "rule",
|
| 1098 |
+
"num_demo": 1,
|
| 1099 |
+
"num_query": 14
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"name": "chess_puzzles_equality",
|
| 1103 |
+
"score": 0.0,
|
| 1104 |
+
"eval_type": "rule",
|
| 1105 |
+
"num_demo": 1,
|
| 1106 |
+
"num_query": 15
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"name": "chess_sygyzy_endgames",
|
| 1110 |
+
"score": 0.09867851446798814,
|
| 1111 |
+
"eval_type": "rule",
|
| 1112 |
+
"num_demo": 1,
|
| 1113 |
+
"num_query": 14
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"name": "chess_winner_identification",
|
| 1117 |
+
"score": 0.3333333333333333,
|
| 1118 |
+
"eval_type": "rule",
|
| 1119 |
+
"num_demo": 1,
|
| 1120 |
+
"num_query": 15
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"name": "chinese_idiom_recognition",
|
| 1124 |
+
"score": 0.2857142857142857,
|
| 1125 |
+
"eval_type": "rule",
|
| 1126 |
+
"num_demo": 1,
|
| 1127 |
+
"num_query": 14
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"name": "circuit_diagram_understanding",
|
| 1131 |
+
"score": 0.4666666666666667,
|
| 1132 |
+
"eval_type": "rule",
|
| 1133 |
+
"num_demo": 1,
|
| 1134 |
+
"num_query": 15
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"name": "clevr_arithmetic",
|
| 1138 |
+
"score": 0.7894736842105263,
|
| 1139 |
+
"eval_type": "rule",
|
| 1140 |
+
"num_demo": 1,
|
| 1141 |
+
"num_query": 19
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"name": "clevrer_moving_direction_video",
|
| 1145 |
+
"score": 0.1875,
|
| 1146 |
+
"eval_type": "rule",
|
| 1147 |
+
"num_demo": 1,
|
| 1148 |
+
"num_query": 16
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"name": "clevrer_object_existence_video",
|
| 1152 |
+
"score": 0.875,
|
| 1153 |
+
"eval_type": "rule",
|
| 1154 |
+
"num_demo": 1,
|
| 1155 |
+
"num_query": 16
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"name": "clevrer_physics",
|
| 1159 |
+
"score": 0.4,
|
| 1160 |
+
"eval_type": "rule",
|
| 1161 |
+
"num_demo": 1,
|
| 1162 |
+
"num_query": 20
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"name": "clevrer_video_moving_object_count",
|
| 1166 |
+
"score": 0.6666666666666666,
|
| 1167 |
+
"eval_type": "rule",
|
| 1168 |
+
"num_demo": 1,
|
| 1169 |
+
"num_query": 21
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"name": "clevrer_video_moving_object_property_recognition",
|
| 1173 |
+
"score": 1.0,
|
| 1174 |
+
"eval_type": "rule",
|
| 1175 |
+
"num_demo": 1,
|
| 1176 |
+
"num_query": 16
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"name": "clip_stable_diffusion_generate",
|
| 1180 |
+
"score": 0.42857142857142855,
|
| 1181 |
+
"eval_type": "rule",
|
| 1182 |
+
"num_demo": 1,
|
| 1183 |
+
"num_query": 14
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"name": "coco_object_detection_by_query_property",
|
| 1187 |
+
"score": 0.4483204700365899,
|
| 1188 |
+
"eval_type": "rule",
|
| 1189 |
+
"num_demo": 1,
|
| 1190 |
+
"num_query": 14
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"name": "coco_ood_global_image_retrieval_by_query_property",
|
| 1194 |
+
"score": 0.7505952380952381,
|
| 1195 |
+
"eval_type": "rule",
|
| 1196 |
+
"num_demo": 0,
|
| 1197 |
+
"num_query": 14
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"name": "coco_person_detection",
|
| 1201 |
+
"score": 0.7107148123741729,
|
| 1202 |
+
"eval_type": "rule",
|
| 1203 |
+
"num_demo": 1,
|
| 1204 |
+
"num_query": 14
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"name": "code_add_tag",
|
| 1208 |
+
"score": 0.3333333333333333,
|
| 1209 |
+
"eval_type": "rule",
|
| 1210 |
+
"num_demo": 1,
|
| 1211 |
+
"num_query": 15
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"name": "code_error_line_identification",
|
| 1215 |
+
"score": 0.35714285714285715,
|
| 1216 |
+
"eval_type": "rule",
|
| 1217 |
+
"num_demo": 1,
|
| 1218 |
+
"num_query": 14
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"name": "code_execution",
|
| 1222 |
+
"score": 0.4375,
|
| 1223 |
+
"eval_type": "rule",
|
| 1224 |
+
"num_demo": 1,
|
| 1225 |
+
"num_query": 16
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"name": "code_match_problem",
|
| 1229 |
+
"score": 0.14285714285714285,
|
| 1230 |
+
"eval_type": "rule",
|
| 1231 |
+
"num_demo": 1,
|
| 1232 |
+
"num_query": 14
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"name": "code_output_result",
|
| 1236 |
+
"score": 0.07142857142857142,
|
| 1237 |
+
"eval_type": "rule",
|
| 1238 |
+
"num_demo": 1,
|
| 1239 |
+
"num_query": 14
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"name": "code_programming_extremely_hard",
|
| 1243 |
+
"score": 0.0,
|
| 1244 |
+
"eval_type": "rule",
|
| 1245 |
+
"num_demo": 1,
|
| 1246 |
+
"num_query": 16
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"name": "code_programming_test_advanced",
|
| 1250 |
+
"score": 0.05555555555555555,
|
| 1251 |
+
"eval_type": "rule",
|
| 1252 |
+
"num_demo": 1,
|
| 1253 |
+
"num_query": 18
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"name": "code_programming_test_easy",
|
| 1257 |
+
"score": 0.16666666666666666,
|
| 1258 |
+
"eval_type": "rule",
|
| 1259 |
+
"num_demo": 1,
|
| 1260 |
+
"num_query": 24
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"name": "code_programming_test_hard",
|
| 1264 |
+
"score": 0.0,
|
| 1265 |
+
"eval_type": "rule",
|
| 1266 |
+
"num_demo": 1,
|
| 1267 |
+
"num_query": 14
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"name": "code_retrieval",
|
| 1271 |
+
"score": 0.35714285714285715,
|
| 1272 |
+
"eval_type": "rule",
|
| 1273 |
+
"num_demo": 1,
|
| 1274 |
+
"num_query": 14
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"name": "code_solution_compare",
|
| 1278 |
+
"score": 0.2857142857142857,
|
| 1279 |
+
"eval_type": "rule",
|
| 1280 |
+
"num_demo": 1,
|
| 1281 |
+
"num_query": 14
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"name": "code_translation_Python",
|
| 1285 |
+
"score": 0.0,
|
| 1286 |
+
"eval_type": "rule",
|
| 1287 |
+
"num_demo": 1,
|
| 1288 |
+
"num_query": 16
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"name": "code_translation_advanced",
|
| 1292 |
+
"score": 0.0,
|
| 1293 |
+
"eval_type": "rule",
|
| 1294 |
+
"num_demo": 1,
|
| 1295 |
+
"num_query": 14
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"name": "code_translation_easy",
|
| 1299 |
+
"score": 0.0,
|
| 1300 |
+
"eval_type": "rule",
|
| 1301 |
+
"num_demo": 1,
|
| 1302 |
+
"num_query": 14
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"name": "code_translation_hard",
|
| 1306 |
+
"score": 0.0,
|
| 1307 |
+
"eval_type": "rule",
|
| 1308 |
+
"num_demo": 1,
|
| 1309 |
+
"num_query": 14
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"name": "code_visualization_output_understanding",
|
| 1313 |
+
"score": 0.3,
|
| 1314 |
+
"eval_type": "rule",
|
| 1315 |
+
"num_demo": 1,
|
| 1316 |
+
"num_query": 10
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"name": "comic_page_ordering",
|
| 1320 |
+
"score": 0.0,
|
| 1321 |
+
"eval_type": "rule",
|
| 1322 |
+
"num_demo": 1,
|
| 1323 |
+
"num_query": 14
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"name": "contain_contain_images",
|
| 1327 |
+
"score": 0.9333333333333333,
|
| 1328 |
+
"eval_type": "rule",
|
| 1329 |
+
"num_demo": 0,
|
| 1330 |
+
"num_query": 15
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"name": "contain_contain_length",
|
| 1334 |
+
"score": 0.8666666666666667,
|
| 1335 |
+
"eval_type": "rule",
|
| 1336 |
+
"num_demo": 0,
|
| 1337 |
+
"num_query": 15
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"name": "contain_length",
|
| 1341 |
+
"score": 0.5333333333333333,
|
| 1342 |
+
"eval_type": "rule",
|
| 1343 |
+
"num_demo": 0,
|
| 1344 |
+
"num_query": 15
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"name": "contain_position_images",
|
| 1348 |
+
"score": 0.6666666666666666,
|
| 1349 |
+
"eval_type": "rule",
|
| 1350 |
+
"num_demo": 0,
|
| 1351 |
+
"num_query": 15
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"name": "contain_position_length",
|
| 1355 |
+
"score": 0.7333333333333333,
|
| 1356 |
+
"eval_type": "rule",
|
| 1357 |
+
"num_demo": 0,
|
| 1358 |
+
"num_query": 15
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"name": "contain_repeat_length",
|
| 1362 |
+
"score": 0.06666666666666667,
|
| 1363 |
+
"eval_type": "rule",
|
| 1364 |
+
"num_demo": 0,
|
| 1365 |
+
"num_query": 15
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"name": "counterfactual_arithmetic",
|
| 1369 |
+
"score": 0.9285714285714286,
|
| 1370 |
+
"eval_type": "rule",
|
| 1371 |
+
"num_demo": 1,
|
| 1372 |
+
"num_query": 14
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"name": "counting_multi_image",
|
| 1376 |
+
"score": 0.5,
|
| 1377 |
+
"eval_type": "rule",
|
| 1378 |
+
"num_demo": 1,
|
| 1379 |
+
"num_query": 14
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"name": "counting_single_image",
|
| 1383 |
+
"score": 0.7857142857142857,
|
| 1384 |
+
"eval_type": "rule",
|
| 1385 |
+
"num_demo": 1,
|
| 1386 |
+
"num_query": 14
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"name": "crossword_mini_5x5",
|
| 1390 |
+
"score": 0.25000000000000006,
|
| 1391 |
+
"eval_type": "rule",
|
| 1392 |
+
"num_demo": 1,
|
| 1393 |
+
"num_query": 14
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"name": "cultural_vqa",
|
| 1397 |
+
"score": 0.4,
|
| 1398 |
+
"eval_type": "rule",
|
| 1399 |
+
"num_demo": 1,
|
| 1400 |
+
"num_query": 15
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"name": "deciphering_oracle_bone",
|
| 1404 |
+
"score": 0.0,
|
| 1405 |
+
"eval_type": "rule",
|
| 1406 |
+
"num_demo": 1,
|
| 1407 |
+
"num_query": 14
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"name": "dish_ingredient_match",
|
| 1411 |
+
"score": 0.6428571428571429,
|
| 1412 |
+
"eval_type": "rule",
|
| 1413 |
+
"num_demo": 1,
|
| 1414 |
+
"num_query": 14
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"name": "distinguish_ai_generated_image",
|
| 1418 |
+
"score": 0.631578947368421,
|
| 1419 |
+
"eval_type": "rule",
|
| 1420 |
+
"num_demo": 1,
|
| 1421 |
+
"num_query": 19
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"name": "dvqa",
|
| 1425 |
+
"score": 0.8947368421052632,
|
| 1426 |
+
"eval_type": "rule",
|
| 1427 |
+
"num_demo": 1,
|
| 1428 |
+
"num_query": 19
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"name": "egocentric_analysis_single_image",
|
| 1432 |
+
"score": 0.5555555555555556,
|
| 1433 |
+
"eval_type": "rule",
|
| 1434 |
+
"num_demo": 1,
|
| 1435 |
+
"num_query": 9
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"name": "egocentric_spatial_reasoning",
|
| 1439 |
+
"score": 0.3333333333333333,
|
| 1440 |
+
"eval_type": "rule",
|
| 1441 |
+
"num_demo": 1,
|
| 1442 |
+
"num_query": 9
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"name": "electricity_future_prediction_from_table",
|
| 1446 |
+
"score": 0.6473684210526315,
|
| 1447 |
+
"eval_type": "rule",
|
| 1448 |
+
"num_demo": 1,
|
| 1449 |
+
"num_query": 19
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"name": "electricity_load_estimate_plot",
|
| 1453 |
+
"score": 0.6612142857142855,
|
| 1454 |
+
"eval_type": "rule",
|
| 1455 |
+
"num_demo": 1,
|
| 1456 |
+
"num_query": 14
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"name": "electricity_plot_future_prediction",
|
| 1460 |
+
"score": 0.9244157894736842,
|
| 1461 |
+
"eval_type": "rule",
|
| 1462 |
+
"num_demo": 1,
|
| 1463 |
+
"num_query": 19
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"name": "emotion_recognition",
|
| 1467 |
+
"score": 0.6428571428571429,
|
| 1468 |
+
"eval_type": "rule",
|
| 1469 |
+
"num_demo": 1,
|
| 1470 |
+
"num_query": 14
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"name": "entertainment_web_game_style",
|
| 1474 |
+
"score": 0.75,
|
| 1475 |
+
"eval_type": "rule",
|
| 1476 |
+
"num_demo": 1,
|
| 1477 |
+
"num_query": 14
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"name": "exchange_rate_estimate_plot",
|
| 1481 |
+
"score": 0.9785871428571429,
|
| 1482 |
+
"eval_type": "rule",
|
| 1483 |
+
"num_demo": 1,
|
| 1484 |
+
"num_query": 14
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"name": "extract_webpage_headline",
|
| 1488 |
+
"score": 0.5714285714285714,
|
| 1489 |
+
"eval_type": "rule",
|
| 1490 |
+
"num_demo": 1,
|
| 1491 |
+
"num_query": 14
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"name": "face_attribute_edit",
|
| 1495 |
+
"score": 0.5,
|
| 1496 |
+
"eval_type": "rule",
|
| 1497 |
+
"num_demo": 1,
|
| 1498 |
+
"num_query": 14
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"name": "face_identity_matching",
|
| 1502 |
+
"score": 0.4,
|
| 1503 |
+
"eval_type": "rule",
|
| 1504 |
+
"num_demo": 1,
|
| 1505 |
+
"num_query": 15
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"name": "face_keypoint_detection",
|
| 1509 |
+
"score": 0.8008804293485591,
|
| 1510 |
+
"eval_type": "rule",
|
| 1511 |
+
"num_demo": 1,
|
| 1512 |
+
"num_query": 14
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"name": "face_swap",
|
| 1516 |
+
"score": 0.6428571428571429,
|
| 1517 |
+
"eval_type": "rule",
|
| 1518 |
+
"num_demo": 1,
|
| 1519 |
+
"num_query": 14
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"name": "famous_building_recognition",
|
| 1523 |
+
"score": 0.875,
|
| 1524 |
+
"eval_type": "rule",
|
| 1525 |
+
"num_demo": 1,
|
| 1526 |
+
"num_query": 16
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"name": "figureqa",
|
| 1530 |
+
"score": 0.5714285714285714,
|
| 1531 |
+
"eval_type": "rule",
|
| 1532 |
+
"num_demo": 1,
|
| 1533 |
+
"num_query": 14
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"name": "finance_table_understanding",
|
| 1537 |
+
"score": 0.5714285714285714,
|
| 1538 |
+
"eval_type": "rule",
|
| 1539 |
+
"num_demo": 1,
|
| 1540 |
+
"num_query": 14
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"name": "flowchart_code_generation",
|
| 1544 |
+
"score": 0.4444444444444444,
|
| 1545 |
+
"eval_type": "rule",
|
| 1546 |
+
"num_demo": 1,
|
| 1547 |
+
"num_query": 9
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"name": "font_recognition",
|
| 1551 |
+
"score": 0.07142857142857142,
|
| 1552 |
+
"eval_type": "rule",
|
| 1553 |
+
"num_demo": 1,
|
| 1554 |
+
"num_query": 14
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"name": "forensic_detection_of_different_images",
|
| 1558 |
+
"score": 0.35714285714285715,
|
| 1559 |
+
"eval_type": "rule",
|
| 1560 |
+
"num_demo": 1,
|
| 1561 |
+
"num_query": 14
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"name": "functionality_matching_in_different_objects",
|
| 1565 |
+
"score": 0.5357142857142857,
|
| 1566 |
+
"eval_type": "rule",
|
| 1567 |
+
"num_demo": 1,
|
| 1568 |
+
"num_query": 14
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"name": "funsd_document_qa",
|
| 1572 |
+
"score": 0.8571428571428571,
|
| 1573 |
+
"eval_type": "rule",
|
| 1574 |
+
"num_demo": 1,
|
| 1575 |
+
"num_query": 14
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"name": "game_info_parsing",
|
| 1579 |
+
"score": 0.8896103896103894,
|
| 1580 |
+
"eval_type": "rule",
|
| 1581 |
+
"num_demo": 1,
|
| 1582 |
+
"num_query": 14
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"name": "game_info_retrieval",
|
| 1586 |
+
"score": 0.6428571428571429,
|
| 1587 |
+
"eval_type": "rule",
|
| 1588 |
+
"num_demo": 0,
|
| 1589 |
+
"num_query": 14
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"name": "game_platform_support_identification",
|
| 1593 |
+
"score": 0.4642857142857143,
|
| 1594 |
+
"eval_type": "rule",
|
| 1595 |
+
"num_demo": 1,
|
| 1596 |
+
"num_query": 14
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"name": "geographic_remote_sensing_land_cover",
|
| 1600 |
+
"score": 0.5714285714285714,
|
| 1601 |
+
"eval_type": "rule",
|
| 1602 |
+
"num_demo": 1,
|
| 1603 |
+
"num_query": 14
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"name": "geometry_analytic",
|
| 1607 |
+
"score": 0.35714285714285715,
|
| 1608 |
+
"eval_type": "rule",
|
| 1609 |
+
"num_demo": 1,
|
| 1610 |
+
"num_query": 14
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"name": "geometry_area",
|
| 1614 |
+
"score": 0.42857142857142855,
|
| 1615 |
+
"eval_type": "rule",
|
| 1616 |
+
"num_demo": 1,
|
| 1617 |
+
"num_query": 14
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"name": "geometry_descriptive",
|
| 1621 |
+
"score": 0.2857142857142857,
|
| 1622 |
+
"eval_type": "rule",
|
| 1623 |
+
"num_demo": 1,
|
| 1624 |
+
"num_query": 14
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"name": "geometry_length",
|
| 1628 |
+
"score": 0.5714285714285714,
|
| 1629 |
+
"eval_type": "rule",
|
| 1630 |
+
"num_demo": 1,
|
| 1631 |
+
"num_query": 14
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"name": "geometry_plot_position_relationship",
|
| 1635 |
+
"score": 0.7857142857142857,
|
| 1636 |
+
"eval_type": "rule",
|
| 1637 |
+
"num_demo": 1,
|
| 1638 |
+
"num_query": 14
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"name": "geometry_reasoning_circled_letter",
|
| 1642 |
+
"score": 0.75,
|
| 1643 |
+
"eval_type": "rule",
|
| 1644 |
+
"num_demo": 1,
|
| 1645 |
+
"num_query": 14
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"name": "geometry_reasoning_count_line_intersections",
|
| 1649 |
+
"score": 0.6071428571428571,
|
| 1650 |
+
"eval_type": "rule",
|
| 1651 |
+
"num_demo": 1,
|
| 1652 |
+
"num_query": 14
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"name": "geometry_reasoning_grid",
|
| 1656 |
+
"score": 0.9642857142857143,
|
| 1657 |
+
"eval_type": "rule",
|
| 1658 |
+
"num_demo": 1,
|
| 1659 |
+
"num_query": 14
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"name": "geometry_reasoning_nested_squares",
|
| 1663 |
+
"score": 0.5357142857142857,
|
| 1664 |
+
"eval_type": "rule",
|
| 1665 |
+
"num_demo": 1,
|
| 1666 |
+
"num_query": 14
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"name": "geometry_reasoning_overlapped_circle",
|
| 1670 |
+
"score": 0.39285714285714285,
|
| 1671 |
+
"eval_type": "rule",
|
| 1672 |
+
"num_demo": 1,
|
| 1673 |
+
"num_query": 14
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"name": "geometry_solid",
|
| 1677 |
+
"score": 0.21428571428571427,
|
| 1678 |
+
"eval_type": "rule",
|
| 1679 |
+
"num_demo": 1,
|
| 1680 |
+
"num_query": 14
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"name": "geometry_transformation",
|
| 1684 |
+
"score": 0.35714285714285715,
|
| 1685 |
+
"eval_type": "rule",
|
| 1686 |
+
"num_demo": 1,
|
| 1687 |
+
"num_query": 14
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"name": "go_capture_stone",
|
| 1691 |
+
"score": 0.13333333333333333,
|
| 1692 |
+
"eval_type": "rule",
|
| 1693 |
+
"num_demo": 1,
|
| 1694 |
+
"num_query": 15
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"name": "google_streetview_circle_reasoning",
|
| 1698 |
+
"score": 0.2,
|
| 1699 |
+
"eval_type": "rule",
|
| 1700 |
+
"num_demo": 1,
|
| 1701 |
+
"num_query": 15
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"name": "google_streetview_circle_sorting",
|
| 1705 |
+
"score": 0.0,
|
| 1706 |
+
"eval_type": "rule",
|
| 1707 |
+
"num_demo": 1,
|
| 1708 |
+
"num_query": 15
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"name": "google_streetview_direction_understanding",
|
| 1712 |
+
"score": 0.7857142857142857,
|
| 1713 |
+
"eval_type": "rule",
|
| 1714 |
+
"num_demo": 1,
|
| 1715 |
+
"num_query": 14
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"name": "google_streetview_line_reasoning",
|
| 1719 |
+
"score": 0.2,
|
| 1720 |
+
"eval_type": "rule",
|
| 1721 |
+
"num_demo": 1,
|
| 1722 |
+
"num_query": 15
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"name": "google_streetview_line_sorting",
|
| 1726 |
+
"score": 0.2,
|
| 1727 |
+
"eval_type": "rule",
|
| 1728 |
+
"num_demo": 1,
|
| 1729 |
+
"num_query": 15
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"name": "graph_chordless_cycle",
|
| 1733 |
+
"score": 0.35714285714285715,
|
| 1734 |
+
"eval_type": "rule",
|
| 1735 |
+
"num_demo": 1,
|
| 1736 |
+
"num_query": 14
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"name": "graph_connectivity",
|
| 1740 |
+
"score": 0.4166666666666667,
|
| 1741 |
+
"eval_type": "rule",
|
| 1742 |
+
"num_demo": 1,
|
| 1743 |
+
"num_query": 15
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"name": "graph_hamiltonian_cycle",
|
| 1747 |
+
"score": 0.49107142857142855,
|
| 1748 |
+
"eval_type": "rule",
|
| 1749 |
+
"num_demo": 1,
|
| 1750 |
+
"num_query": 14
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"name": "graph_hamiltonian_path",
|
| 1754 |
+
"score": 0.45833333333333337,
|
| 1755 |
+
"eval_type": "rule",
|
| 1756 |
+
"num_demo": 1,
|
| 1757 |
+
"num_query": 14
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"name": "graph_isomorphism",
|
| 1761 |
+
"score": 0.5333333333333333,
|
| 1762 |
+
"eval_type": "rule",
|
| 1763 |
+
"num_demo": 1,
|
| 1764 |
+
"num_query": 15
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"name": "graph_maxflow",
|
| 1768 |
+
"score": 0.3333333333333333,
|
| 1769 |
+
"eval_type": "rule",
|
| 1770 |
+
"num_demo": 1,
|
| 1771 |
+
"num_query": 15
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"name": "graph_shortest_path_kamada_kawai",
|
| 1775 |
+
"score": 0.42857142857142855,
|
| 1776 |
+
"eval_type": "rule",
|
| 1777 |
+
"num_demo": 1,
|
| 1778 |
+
"num_query": 14
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"name": "graph_shortest_path_planar",
|
| 1782 |
+
"score": 0.5714285714285714,
|
| 1783 |
+
"eval_type": "rule",
|
| 1784 |
+
"num_demo": 1,
|
| 1785 |
+
"num_query": 14
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"name": "graph_theory",
|
| 1789 |
+
"score": 0.5714285714285714,
|
| 1790 |
+
"eval_type": "rule",
|
| 1791 |
+
"num_demo": 1,
|
| 1792 |
+
"num_query": 14
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"name": "handwritten_math_expression_extraction",
|
| 1796 |
+
"score": 0.7142857142857143,
|
| 1797 |
+
"eval_type": "rule",
|
| 1798 |
+
"num_demo": 1,
|
| 1799 |
+
"num_query": 14
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"name": "hashtag_recommendation",
|
| 1803 |
+
"score": 0.9107142857142857,
|
| 1804 |
+
"eval_type": "rule",
|
| 1805 |
+
"num_demo": 1,
|
| 1806 |
+
"num_query": 14
|
| 1807 |
+
},
|
| 1808 |
+
{
|
| 1809 |
+
"name": "healthcare_info_judgement",
|
| 1810 |
+
"score": 0.7857142857142857,
|
| 1811 |
+
"eval_type": "rule",
|
| 1812 |
+
"num_demo": 1,
|
| 1813 |
+
"num_query": 14
|
| 1814 |
+
},
|
| 1815 |
+
{
|
| 1816 |
+
"name": "highest_discount_game_price_identification",
|
| 1817 |
+
"score": 1.0,
|
| 1818 |
+
"eval_type": "rule",
|
| 1819 |
+
"num_demo": 1,
|
| 1820 |
+
"num_query": 14
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"name": "hotel_booking_confirmation_parsing",
|
| 1824 |
+
"score": 0.7077922077922079,
|
| 1825 |
+
"eval_type": "rule",
|
| 1826 |
+
"num_demo": 1,
|
| 1827 |
+
"num_query": 14
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"name": "human_relationship_reasoning",
|
| 1831 |
+
"score": 0.9285714285714286,
|
| 1832 |
+
"eval_type": "rule",
|
| 1833 |
+
"num_demo": 1,
|
| 1834 |
+
"num_query": 14
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"name": "humor_understand_caption_match",
|
| 1838 |
+
"score": 0.6,
|
| 1839 |
+
"eval_type": "rule",
|
| 1840 |
+
"num_demo": 1,
|
| 1841 |
+
"num_query": 15
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"name": "icon_arithmetic_puzzle",
|
| 1845 |
+
"score": 0.9642857142857143,
|
| 1846 |
+
"eval_type": "rule",
|
| 1847 |
+
"num_demo": 1,
|
| 1848 |
+
"num_query": 14
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"name": "iconqa_count_and_reasoning",
|
| 1852 |
+
"score": 0.6842105263157895,
|
| 1853 |
+
"eval_type": "rule",
|
| 1854 |
+
"num_demo": 1,
|
| 1855 |
+
"num_query": 19
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"name": "ili_ratio_future_prediction",
|
| 1859 |
+
"score": 0.24864285714285697,
|
| 1860 |
+
"eval_type": "rule",
|
| 1861 |
+
"num_demo": 1,
|
| 1862 |
+
"num_query": 14
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"name": "image_style_recognition",
|
| 1866 |
+
"score": 1.0,
|
| 1867 |
+
"eval_type": "rule",
|
| 1868 |
+
"num_demo": 1,
|
| 1869 |
+
"num_query": 14
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"name": "image_translation_en2cn",
|
| 1873 |
+
"score": 0.4404063008108421,
|
| 1874 |
+
"eval_type": "rule",
|
| 1875 |
+
"num_demo": 1,
|
| 1876 |
+
"num_query": 9
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"name": "insect_order_classification",
|
| 1880 |
+
"score": 0.26666666666666666,
|
| 1881 |
+
"eval_type": "rule",
|
| 1882 |
+
"num_demo": 1,
|
| 1883 |
+
"num_query": 15
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"name": "interpret_force_perspective_illusion",
|
| 1887 |
+
"score": 0.6666666666666666,
|
| 1888 |
+
"eval_type": "rule",
|
| 1889 |
+
"num_demo": 1,
|
| 1890 |
+
"num_query": 15
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"name": "ishihara_test",
|
| 1894 |
+
"score": 0.2857142857142857,
|
| 1895 |
+
"eval_type": "rule",
|
| 1896 |
+
"num_demo": 1,
|
| 1897 |
+
"num_query": 14
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"name": "knowledge_graph_understanding",
|
| 1901 |
+
"score": 0.4,
|
| 1902 |
+
"eval_type": "rule",
|
| 1903 |
+
"num_demo": 0,
|
| 1904 |
+
"num_query": 15
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"name": "knowledge_sign_recognition",
|
| 1908 |
+
"score": 0.4444444444444444,
|
| 1909 |
+
"eval_type": "rule",
|
| 1910 |
+
"num_demo": 1,
|
| 1911 |
+
"num_query": 9
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"name": "kvqa_knowledge_aware_qa",
|
| 1915 |
+
"score": 0.42105263157894735,
|
| 1916 |
+
"eval_type": "rule",
|
| 1917 |
+
"num_demo": 1,
|
| 1918 |
+
"num_query": 19
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"name": "landmark_check_two_images",
|
| 1922 |
+
"score": 0.8222222222222223,
|
| 1923 |
+
"eval_type": "rule",
|
| 1924 |
+
"num_demo": 1,
|
| 1925 |
+
"num_query": 15
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"name": "landmark_recognition_and_qa",
|
| 1929 |
+
"score": 0.5333333333333333,
|
| 1930 |
+
"eval_type": "rule",
|
| 1931 |
+
"num_demo": 1,
|
| 1932 |
+
"num_query": 15
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"name": "latex_complex_formula_convertion",
|
| 1936 |
+
"score": 0.47058823529411764,
|
| 1937 |
+
"eval_type": "rule",
|
| 1938 |
+
"num_demo": 1,
|
| 1939 |
+
"num_query": 17
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"name": "license_plate_recognition",
|
| 1943 |
+
"score": 0.7142857142857143,
|
| 1944 |
+
"eval_type": "rule",
|
| 1945 |
+
"num_demo": 1,
|
| 1946 |
+
"num_query": 14
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"name": "llavaguard",
|
| 1950 |
+
"score": 0.6071428571428571,
|
| 1951 |
+
"eval_type": "rule",
|
| 1952 |
+
"num_demo": 1,
|
| 1953 |
+
"num_query": 14
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"name": "location_vqa",
|
| 1957 |
+
"score": 0.6428571428571429,
|
| 1958 |
+
"eval_type": "rule",
|
| 1959 |
+
"num_demo": 1,
|
| 1960 |
+
"num_query": 14
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"name": "logical_reasoning_2D_views_of_3D_shapes",
|
| 1964 |
+
"score": 0.14285714285714285,
|
| 1965 |
+
"eval_type": "rule",
|
| 1966 |
+
"num_demo": 1,
|
| 1967 |
+
"num_query": 14
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"name": "logical_reasoning_2d_folding",
|
| 1971 |
+
"score": 0.2857142857142857,
|
| 1972 |
+
"eval_type": "rule",
|
| 1973 |
+
"num_demo": 1,
|
| 1974 |
+
"num_query": 14
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"name": "logical_reasoning_find_odd_one_out",
|
| 1978 |
+
"score": 0.0,
|
| 1979 |
+
"eval_type": "rule",
|
| 1980 |
+
"num_demo": 1,
|
| 1981 |
+
"num_query": 14
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"name": "logical_reasoning_fit_pattern",
|
| 1985 |
+
"score": 0.5,
|
| 1986 |
+
"eval_type": "rule",
|
| 1987 |
+
"num_demo": 1,
|
| 1988 |
+
"num_query": 14
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"name": "logo2k_same_type_logo_retrieval",
|
| 1992 |
+
"score": 0.8928571428571429,
|
| 1993 |
+
"eval_type": "rule",
|
| 1994 |
+
"num_demo": 1,
|
| 1995 |
+
"num_query": 14
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"name": "long_string_letter_recognition",
|
| 1999 |
+
"score": 0.0,
|
| 2000 |
+
"eval_type": "rule",
|
| 2001 |
+
"num_demo": 1,
|
| 2002 |
+
"num_query": 14
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"name": "long_string_number_recognition",
|
| 2006 |
+
"score": 0.35714285714285715,
|
| 2007 |
+
"eval_type": "rule",
|
| 2008 |
+
"num_demo": 1,
|
| 2009 |
+
"num_query": 14
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"name": "mahjong",
|
| 2013 |
+
"score": 0.0,
|
| 2014 |
+
"eval_type": "rule",
|
| 2015 |
+
"num_demo": 1,
|
| 2016 |
+
"num_query": 14
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"name": "map_diagram_qa",
|
| 2020 |
+
"score": 0.7142857142857143,
|
| 2021 |
+
"eval_type": "rule",
|
| 2022 |
+
"num_demo": 1,
|
| 2023 |
+
"num_query": 14
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"name": "math_breakpoint",
|
| 2027 |
+
"score": 0.6666666666666666,
|
| 2028 |
+
"eval_type": "rule",
|
| 2029 |
+
"num_demo": 1,
|
| 2030 |
+
"num_query": 15
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"name": "math_convexity_value_estimation",
|
| 2034 |
+
"score": 0.47324110707388967,
|
| 2035 |
+
"eval_type": "rule",
|
| 2036 |
+
"num_demo": 1,
|
| 2037 |
+
"num_query": 15
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"name": "math_exams_v",
|
| 2041 |
+
"score": 0.6428571428571429,
|
| 2042 |
+
"eval_type": "rule",
|
| 2043 |
+
"num_demo": 1,
|
| 2044 |
+
"num_query": 14
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"name": "math_parity",
|
| 2048 |
+
"score": 0.7333333333333333,
|
| 2049 |
+
"eval_type": "rule",
|
| 2050 |
+
"num_demo": 1,
|
| 2051 |
+
"num_query": 15
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"name": "maze_2d_8x8",
|
| 2055 |
+
"score": 0.0,
|
| 2056 |
+
"eval_type": "rule",
|
| 2057 |
+
"num_demo": 1,
|
| 2058 |
+
"num_query": 14
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"name": "media_homepage_profile",
|
| 2062 |
+
"score": 0.2585034013605442,
|
| 2063 |
+
"eval_type": "rule",
|
| 2064 |
+
"num_demo": 0,
|
| 2065 |
+
"num_query": 14
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"name": "media_recommend_solutions_stackoverflow",
|
| 2069 |
+
"score": 0.9285714285714286,
|
| 2070 |
+
"eval_type": "rule",
|
| 2071 |
+
"num_demo": 1,
|
| 2072 |
+
"num_query": 14
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"name": "medical_abdomen_MRI_organ_recognition",
|
| 2076 |
+
"score": 0.2619047619047619,
|
| 2077 |
+
"eval_type": "rule",
|
| 2078 |
+
"num_demo": 1,
|
| 2079 |
+
"num_query": 14
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"name": "medical_abdomen_endscopy_organ_recognition",
|
| 2083 |
+
"score": 0.11904761904761904,
|
| 2084 |
+
"eval_type": "rule",
|
| 2085 |
+
"num_demo": 1,
|
| 2086 |
+
"num_query": 14
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"name": "medical_blood_vessels_recognition",
|
| 2090 |
+
"score": 0.5,
|
| 2091 |
+
"eval_type": "rule",
|
| 2092 |
+
"num_demo": 1,
|
| 2093 |
+
"num_query": 14
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"name": "medical_cell_recognition",
|
| 2097 |
+
"score": 0.42857142857142855,
|
| 2098 |
+
"eval_type": "rule",
|
| 2099 |
+
"num_demo": 1,
|
| 2100 |
+
"num_query": 14
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"name": "medical_content_based_retrieval_radiology",
|
| 2104 |
+
"score": 0.2857142857142857,
|
| 2105 |
+
"eval_type": "rule",
|
| 2106 |
+
"num_demo": 1,
|
| 2107 |
+
"num_query": 14
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"name": "medical_counting_lymphocytes",
|
| 2111 |
+
"score": 0.0,
|
| 2112 |
+
"eval_type": "rule",
|
| 2113 |
+
"num_demo": 1,
|
| 2114 |
+
"num_query": 14
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"name": "medical_image_artifacts_indentification",
|
| 2118 |
+
"score": 0.21428571428571427,
|
| 2119 |
+
"eval_type": "rule",
|
| 2120 |
+
"num_demo": 1,
|
| 2121 |
+
"num_query": 14
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"name": "medical_keywords_based_retrieval_non_radiology",
|
| 2125 |
+
"score": 0.2857142857142857,
|
| 2126 |
+
"eval_type": "rule",
|
| 2127 |
+
"num_demo": 1,
|
| 2128 |
+
"num_query": 14
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"name": "medical_multi_organ_segmentation_rater",
|
| 2132 |
+
"score": 0.35714285714285715,
|
| 2133 |
+
"eval_type": "rule",
|
| 2134 |
+
"num_demo": 1,
|
| 2135 |
+
"num_query": 14
|
| 2136 |
+
},
|
| 2137 |
+
{
|
| 2138 |
+
"name": "medical_parasite_detection",
|
| 2139 |
+
"score": 0.2857142857142857,
|
| 2140 |
+
"eval_type": "rule",
|
| 2141 |
+
"num_demo": 1,
|
| 2142 |
+
"num_query": 14
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"name": "medical_polyp_segmentation_single_object_rater",
|
| 2146 |
+
"score": 0.5,
|
| 2147 |
+
"eval_type": "rule",
|
| 2148 |
+
"num_demo": 1,
|
| 2149 |
+
"num_query": 14
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"name": "medical_retrieval_given_surgeon_activity",
|
| 2153 |
+
"score": 0.35714285714285715,
|
| 2154 |
+
"eval_type": "rule",
|
| 2155 |
+
"num_demo": 1,
|
| 2156 |
+
"num_query": 14
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"name": "memorization_chinese_celebrity",
|
| 2160 |
+
"score": 0.2857142857142857,
|
| 2161 |
+
"eval_type": "rule",
|
| 2162 |
+
"num_demo": 1,
|
| 2163 |
+
"num_query": 14
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"name": "memorization_famous_treaty",
|
| 2167 |
+
"score": 0.32142857142857145,
|
| 2168 |
+
"eval_type": "rule",
|
| 2169 |
+
"num_demo": 1,
|
| 2170 |
+
"num_query": 14
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"name": "memorization_indian_celebrity",
|
| 2174 |
+
"score": 0.35714285714285715,
|
| 2175 |
+
"eval_type": "rule",
|
| 2176 |
+
"num_demo": 1,
|
| 2177 |
+
"num_query": 14
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"name": "memorization_papers",
|
| 2181 |
+
"score": 0.4,
|
| 2182 |
+
"eval_type": "rule",
|
| 2183 |
+
"num_demo": 1,
|
| 2184 |
+
"num_query": 15
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"name": "mensa_iq_test",
|
| 2188 |
+
"score": 0.2693850267379679,
|
| 2189 |
+
"eval_type": "rule",
|
| 2190 |
+
"num_demo": 1,
|
| 2191 |
+
"num_query": 17
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"name": "mindmap_elements_parsing",
|
| 2195 |
+
"score": 0.2857142857142857,
|
| 2196 |
+
"eval_type": "rule",
|
| 2197 |
+
"num_demo": 1,
|
| 2198 |
+
"num_query": 14
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"name": "mnist_pattern",
|
| 2202 |
+
"score": 0.5,
|
| 2203 |
+
"eval_type": "rule",
|
| 2204 |
+
"num_demo": 1,
|
| 2205 |
+
"num_query": 14
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"name": "monthly_weather_days_count",
|
| 2209 |
+
"score": 0.40476190476190477,
|
| 2210 |
+
"eval_type": "rule",
|
| 2211 |
+
"num_demo": 1,
|
| 2212 |
+
"num_query": 14
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"name": "move_pos_to_pos_hanoi_4_pole",
|
| 2216 |
+
"score": 0.0,
|
| 2217 |
+
"eval_type": "rule",
|
| 2218 |
+
"num_demo": 1,
|
| 2219 |
+
"num_query": 14
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"name": "movie_info_parsing",
|
| 2223 |
+
"score": 0.6607142857142857,
|
| 2224 |
+
"eval_type": "rule",
|
| 2225 |
+
"num_demo": 1,
|
| 2226 |
+
"num_query": 14
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"name": "movie_info_retrieval",
|
| 2230 |
+
"score": 0.7857142857142857,
|
| 2231 |
+
"eval_type": "rule",
|
| 2232 |
+
"num_demo": 0,
|
| 2233 |
+
"num_query": 14
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"name": "movie_retrieval_by_actor",
|
| 2237 |
+
"score": 0.7142857142857143,
|
| 2238 |
+
"eval_type": "rule",
|
| 2239 |
+
"num_demo": 0,
|
| 2240 |
+
"num_query": 14
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"name": "multi_contain_position_only",
|
| 2244 |
+
"score": 0.06666666666666667,
|
| 2245 |
+
"eval_type": "rule",
|
| 2246 |
+
"num_demo": 0,
|
| 2247 |
+
"num_query": 15
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"name": "multi_contain_repeat",
|
| 2251 |
+
"score": 0.06666666666666667,
|
| 2252 |
+
"eval_type": "rule",
|
| 2253 |
+
"num_demo": 0,
|
| 2254 |
+
"num_query": 15
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"name": "multi_contain_repeat_position_only_length",
|
| 2258 |
+
"score": 0.06666666666666667,
|
| 2259 |
+
"eval_type": "rule",
|
| 2260 |
+
"num_demo": 0,
|
| 2261 |
+
"num_query": 15
|
| 2262 |
+
},
|
| 2263 |
+
{
|
| 2264 |
+
"name": "multi_load_type_prediction_from_plot",
|
| 2265 |
+
"score": 0.5119047619047618,
|
| 2266 |
+
"eval_type": "rule",
|
| 2267 |
+
"num_demo": 1,
|
| 2268 |
+
"num_query": 14
|
| 2269 |
+
},
|
| 2270 |
+
{
|
| 2271 |
+
"name": "multilingual_game_info_parsing",
|
| 2272 |
+
"score": 0.6607142857142857,
|
| 2273 |
+
"eval_type": "rule",
|
| 2274 |
+
"num_demo": 1,
|
| 2275 |
+
"num_query": 14
|
| 2276 |
+
},
|
| 2277 |
+
{
|
| 2278 |
+
"name": "multilingual_movie_info_parsing",
|
| 2279 |
+
"score": 0.6224489795918366,
|
| 2280 |
+
"eval_type": "rule",
|
| 2281 |
+
"num_demo": 1,
|
| 2282 |
+
"num_query": 14
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"name": "multilingual_news_qa",
|
| 2286 |
+
"score": 0.9285714285714286,
|
| 2287 |
+
"eval_type": "rule",
|
| 2288 |
+
"num_demo": 0,
|
| 2289 |
+
"num_query": 14
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"name": "multiple_states_identify_africa",
|
| 2293 |
+
"score": 0.41428571428571426,
|
| 2294 |
+
"eval_type": "rule",
|
| 2295 |
+
"num_demo": 1,
|
| 2296 |
+
"num_query": 14
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"name": "multiple_states_identify_americas",
|
| 2300 |
+
"score": 0.4,
|
| 2301 |
+
"eval_type": "rule",
|
| 2302 |
+
"num_demo": 1,
|
| 2303 |
+
"num_query": 14
|
| 2304 |
+
},
|
| 2305 |
+
{
|
| 2306 |
+
"name": "multiple_states_identify_asia",
|
| 2307 |
+
"score": 0.5142857142857142,
|
| 2308 |
+
"eval_type": "rule",
|
| 2309 |
+
"num_demo": 1,
|
| 2310 |
+
"num_query": 14
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"name": "multiple_states_identify_europe",
|
| 2314 |
+
"score": 0.5428571428571429,
|
| 2315 |
+
"eval_type": "rule",
|
| 2316 |
+
"num_demo": 1,
|
| 2317 |
+
"num_query": 14
|
| 2318 |
+
},
|
| 2319 |
+
{
|
| 2320 |
+
"name": "multiview_reasoning_camera_moving",
|
| 2321 |
+
"score": 0.7857142857142857,
|
| 2322 |
+
"eval_type": "rule",
|
| 2323 |
+
"num_demo": 1,
|
| 2324 |
+
"num_query": 14
|
| 2325 |
+
},
|
| 2326 |
+
{
|
| 2327 |
+
"name": "muma_theory_of_mind_belief_of_goal",
|
| 2328 |
+
"score": 0.0,
|
| 2329 |
+
"eval_type": "rule",
|
| 2330 |
+
"num_demo": 1,
|
| 2331 |
+
"num_query": 15
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"name": "muma_theory_of_mind_social_goal",
|
| 2335 |
+
"score": 0.0,
|
| 2336 |
+
"eval_type": "rule",
|
| 2337 |
+
"num_demo": 1,
|
| 2338 |
+
"num_query": 15
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"name": "music_info_parsing",
|
| 2342 |
+
"score": 0.7142857142857143,
|
| 2343 |
+
"eval_type": "rule",
|
| 2344 |
+
"num_demo": 1,
|
| 2345 |
+
"num_query": 14
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"name": "music_info_retrieval",
|
| 2349 |
+
"score": 0.5,
|
| 2350 |
+
"eval_type": "rule",
|
| 2351 |
+
"num_demo": 0,
|
| 2352 |
+
"num_query": 14
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"name": "music_sheet_author",
|
| 2356 |
+
"score": 0.1875,
|
| 2357 |
+
"eval_type": "rule",
|
| 2358 |
+
"num_demo": 1,
|
| 2359 |
+
"num_query": 16
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"name": "music_sheet_format_QA",
|
| 2363 |
+
"score": 0.35714285714285715,
|
| 2364 |
+
"eval_type": "rule",
|
| 2365 |
+
"num_demo": 1,
|
| 2366 |
+
"num_query": 14
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"name": "music_sheet_name",
|
| 2370 |
+
"score": 0.26666666666666666,
|
| 2371 |
+
"eval_type": "rule",
|
| 2372 |
+
"num_demo": 1,
|
| 2373 |
+
"num_query": 15
|
| 2374 |
+
},
|
| 2375 |
+
{
|
| 2376 |
+
"name": "music_sheet_note_count",
|
| 2377 |
+
"score": 0.058823529411764705,
|
| 2378 |
+
"eval_type": "rule",
|
| 2379 |
+
"num_demo": 1,
|
| 2380 |
+
"num_query": 17
|
| 2381 |
+
},
|
| 2382 |
+
{
|
| 2383 |
+
"name": "music_sheet_sentiment",
|
| 2384 |
+
"score": 0.2857142857142857,
|
| 2385 |
+
"eval_type": "rule",
|
| 2386 |
+
"num_demo": 1,
|
| 2387 |
+
"num_query": 14
|
| 2388 |
+
},
|
| 2389 |
+
{
|
| 2390 |
+
"name": "mvsa_sentiment_classification",
|
| 2391 |
+
"score": 0.6428571428571429,
|
| 2392 |
+
"eval_type": "rule",
|
| 2393 |
+
"num_demo": 1,
|
| 2394 |
+
"num_query": 14
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"name": "newspaper_ocr_in_query_box",
|
| 2398 |
+
"score": 0.4666666666666667,
|
| 2399 |
+
"eval_type": "rule",
|
| 2400 |
+
"num_demo": 1,
|
| 2401 |
+
"num_query": 15
|
| 2402 |
+
},
|
| 2403 |
+
{
|
| 2404 |
+
"name": "newspaper_page_parse_and_count",
|
| 2405 |
+
"score": 0.5333333333333333,
|
| 2406 |
+
"eval_type": "rule",
|
| 2407 |
+
"num_demo": 1,
|
| 2408 |
+
"num_query": 15
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"name": "next_action_prediction",
|
| 2412 |
+
"score": 0.5,
|
| 2413 |
+
"eval_type": "rule",
|
| 2414 |
+
"num_demo": 1,
|
| 2415 |
+
"num_query": 14
|
| 2416 |
+
},
|
| 2417 |
+
{
|
| 2418 |
+
"name": "nextqa_mc",
|
| 2419 |
+
"score": 0.9473684210526315,
|
| 2420 |
+
"eval_type": "rule",
|
| 2421 |
+
"num_demo": 1,
|
| 2422 |
+
"num_query": 19
|
| 2423 |
+
},
|
| 2424 |
+
{
|
| 2425 |
+
"name": "nlvr2_two_image_compare_qa",
|
| 2426 |
+
"score": 0.7857142857142857,
|
| 2427 |
+
"eval_type": "rule",
|
| 2428 |
+
"num_demo": 1,
|
| 2429 |
+
"num_query": 14
|
| 2430 |
+
},
|
| 2431 |
+
{
|
| 2432 |
+
"name": "number_comparison",
|
| 2433 |
+
"score": 1.0,
|
| 2434 |
+
"eval_type": "rule",
|
| 2435 |
+
"num_demo": 0,
|
| 2436 |
+
"num_query": 14
|
| 2437 |
+
},
|
| 2438 |
+
{
|
| 2439 |
+
"name": "number_puzzle_kakuro_5x5",
|
| 2440 |
+
"score": 0.0,
|
| 2441 |
+
"eval_type": "rule",
|
| 2442 |
+
"num_demo": 1,
|
| 2443 |
+
"num_query": 15
|
| 2444 |
+
},
|
| 2445 |
+
{
|
| 2446 |
+
"name": "number_puzzle_sudoku",
|
| 2447 |
+
"score": 0.0,
|
| 2448 |
+
"eval_type": "rule",
|
| 2449 |
+
"num_demo": 1,
|
| 2450 |
+
"num_query": 15
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"name": "ocr_article_authors",
|
| 2454 |
+
"score": 0.5,
|
| 2455 |
+
"eval_type": "rule",
|
| 2456 |
+
"num_demo": 1,
|
| 2457 |
+
"num_query": 14
|
| 2458 |
+
},
|
| 2459 |
+
{
|
| 2460 |
+
"name": "ocr_article_journal",
|
| 2461 |
+
"score": 0.42857142857142855,
|
| 2462 |
+
"eval_type": "rule",
|
| 2463 |
+
"num_demo": 1,
|
| 2464 |
+
"num_query": 14
|
| 2465 |
+
},
|
| 2466 |
+
{
|
| 2467 |
+
"name": "ocr_math_equation",
|
| 2468 |
+
"score": 0.5714285714285714,
|
| 2469 |
+
"eval_type": "rule",
|
| 2470 |
+
"num_demo": 1,
|
| 2471 |
+
"num_query": 14
|
| 2472 |
+
},
|
| 2473 |
+
{
|
| 2474 |
+
"name": "ocr_math_text_latex",
|
| 2475 |
+
"score": 0.21428571428571427,
|
| 2476 |
+
"eval_type": "rule",
|
| 2477 |
+
"num_demo": 1,
|
| 2478 |
+
"num_query": 14
|
| 2479 |
+
},
|
| 2480 |
+
{
|
| 2481 |
+
"name": "ocr_resume_employer_plain",
|
| 2482 |
+
"score": 0.6428571428571429,
|
| 2483 |
+
"eval_type": "rule",
|
| 2484 |
+
"num_demo": 1,
|
| 2485 |
+
"num_query": 14
|
| 2486 |
+
},
|
| 2487 |
+
{
|
| 2488 |
+
"name": "ocr_resume_experience_plain",
|
| 2489 |
+
"score": 0.6428571428571429,
|
| 2490 |
+
"eval_type": "rule",
|
| 2491 |
+
"num_demo": 1,
|
| 2492 |
+
"num_query": 14
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"name": "ocr_resume_school_plain",
|
| 2496 |
+
"score": 0.5,
|
| 2497 |
+
"eval_type": "rule",
|
| 2498 |
+
"num_demo": 1,
|
| 2499 |
+
"num_query": 14
|
| 2500 |
+
},
|
| 2501 |
+
{
|
| 2502 |
+
"name": "ocr_resume_skill_plain",
|
| 2503 |
+
"score": 0.35714285714285715,
|
| 2504 |
+
"eval_type": "rule",
|
| 2505 |
+
"num_demo": 1,
|
| 2506 |
+
"num_query": 14
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"name": "ocr_table_to_csv",
|
| 2510 |
+
"score": 0.5714285714285714,
|
| 2511 |
+
"eval_type": "rule",
|
| 2512 |
+
"num_demo": 1,
|
| 2513 |
+
"num_query": 14
|
| 2514 |
+
},
|
| 2515 |
+
{
|
| 2516 |
+
"name": "ocr_table_to_html",
|
| 2517 |
+
"score": 0.6428571428571429,
|
| 2518 |
+
"eval_type": "rule",
|
| 2519 |
+
"num_demo": 1,
|
| 2520 |
+
"num_query": 14
|
| 2521 |
+
},
|
| 2522 |
+
{
|
| 2523 |
+
"name": "ocr_table_to_latex",
|
| 2524 |
+
"score": 0.6428571428571429,
|
| 2525 |
+
"eval_type": "rule",
|
| 2526 |
+
"num_demo": 1,
|
| 2527 |
+
"num_query": 14
|
| 2528 |
+
},
|
| 2529 |
+
{
|
| 2530 |
+
"name": "ocr_table_to_markdown",
|
| 2531 |
+
"score": 0.9285714285714286,
|
| 2532 |
+
"eval_type": "rule",
|
| 2533 |
+
"num_demo": 1,
|
| 2534 |
+
"num_query": 14
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"name": "orchestra_score_recognition",
|
| 2538 |
+
"score": 0.07142857142857142,
|
| 2539 |
+
"eval_type": "rule",
|
| 2540 |
+
"num_demo": 1,
|
| 2541 |
+
"num_query": 14
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"name": "out_of_context",
|
| 2545 |
+
"score": 0.7857142857142857,
|
| 2546 |
+
"eval_type": "rule",
|
| 2547 |
+
"num_demo": 1,
|
| 2548 |
+
"num_query": 14
|
| 2549 |
+
},
|
| 2550 |
+
{
|
| 2551 |
+
"name": "painting_QA",
|
| 2552 |
+
"score": 0.7142857142857143,
|
| 2553 |
+
"eval_type": "rule",
|
| 2554 |
+
"num_demo": 1,
|
| 2555 |
+
"num_query": 14
|
| 2556 |
+
},
|
| 2557 |
+
{
|
| 2558 |
+
"name": "panel_images_multi_question",
|
| 2559 |
+
"score": 0.7142857142857142,
|
| 2560 |
+
"eval_type": "rule",
|
| 2561 |
+
"num_demo": 1,
|
| 2562 |
+
"num_query": 14
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"name": "panel_images_single_question",
|
| 2566 |
+
"score": 0.9285714285714286,
|
| 2567 |
+
"eval_type": "rule",
|
| 2568 |
+
"num_demo": 1,
|
| 2569 |
+
"num_query": 14
|
| 2570 |
+
},
|
| 2571 |
+
{
|
| 2572 |
+
"name": "paper_review_acceptance",
|
| 2573 |
+
"score": 0.4666666666666667,
|
| 2574 |
+
"eval_type": "rule",
|
| 2575 |
+
"num_demo": 1,
|
| 2576 |
+
"num_query": 15
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"name": "paper_review_rating",
|
| 2580 |
+
"score": 0.6634733643689834,
|
| 2581 |
+
"eval_type": "rule",
|
| 2582 |
+
"num_demo": 1,
|
| 2583 |
+
"num_query": 15
|
| 2584 |
+
},
|
| 2585 |
+
{
|
| 2586 |
+
"name": "paper_vqa",
|
| 2587 |
+
"score": 0.2857142857142857,
|
| 2588 |
+
"eval_type": "rule",
|
| 2589 |
+
"num_demo": 1,
|
| 2590 |
+
"num_query": 14
|
| 2591 |
+
},
|
| 2592 |
+
{
|
| 2593 |
+
"name": "perception_test_object_shuffle_video",
|
| 2594 |
+
"score": 0.1875,
|
| 2595 |
+
"eval_type": "rule",
|
| 2596 |
+
"num_demo": 1,
|
| 2597 |
+
"num_query": 16
|
| 2598 |
+
},
|
| 2599 |
+
{
|
| 2600 |
+
"name": "perception_test_video_action_count",
|
| 2601 |
+
"score": 0.375,
|
| 2602 |
+
"eval_type": "rule",
|
| 2603 |
+
"num_demo": 1,
|
| 2604 |
+
"num_query": 16
|
| 2605 |
+
},
|
| 2606 |
+
{
|
| 2607 |
+
"name": "perception_test_video_character_order",
|
| 2608 |
+
"score": 0.75,
|
| 2609 |
+
"eval_type": "rule",
|
| 2610 |
+
"num_demo": 1,
|
| 2611 |
+
"num_query": 16
|
| 2612 |
+
},
|
| 2613 |
+
{
|
| 2614 |
+
"name": "photo_sharing_image_retrieval",
|
| 2615 |
+
"score": 0.7857142857142857,
|
| 2616 |
+
"eval_type": "rule",
|
| 2617 |
+
"num_demo": 0,
|
| 2618 |
+
"num_query": 14
|
| 2619 |
+
},
|
| 2620 |
+
{
|
| 2621 |
+
"name": "photoshop_operation",
|
| 2622 |
+
"score": 0.2928571428571428,
|
| 2623 |
+
"eval_type": "rule",
|
| 2624 |
+
"num_demo": 1,
|
| 2625 |
+
"num_query": 14
|
| 2626 |
+
},
|
| 2627 |
+
{
|
| 2628 |
+
"name": "physical_property_reasoning",
|
| 2629 |
+
"score": 0.9285714285714286,
|
| 2630 |
+
"eval_type": "rule",
|
| 2631 |
+
"num_demo": 1,
|
| 2632 |
+
"num_query": 14
|
| 2633 |
+
},
|
| 2634 |
+
{
|
| 2635 |
+
"name": "physics_exams_v",
|
| 2636 |
+
"score": 0.35714285714285715,
|
| 2637 |
+
"eval_type": "rule",
|
| 2638 |
+
"num_demo": 1,
|
| 2639 |
+
"num_query": 14
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"name": "pictionary_cartoon_drawing_guess",
|
| 2643 |
+
"score": 0.5714285714285714,
|
| 2644 |
+
"eval_type": "rule",
|
| 2645 |
+
"num_demo": 1,
|
| 2646 |
+
"num_query": 14
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"name": "pictionary_chinese_food_img2en",
|
| 2650 |
+
"score": 0.2857142857142857,
|
| 2651 |
+
"eval_type": "rule",
|
| 2652 |
+
"num_demo": 1,
|
| 2653 |
+
"num_query": 14
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"name": "pictionary_doodle_guess",
|
| 2657 |
+
"score": 0.0,
|
| 2658 |
+
"eval_type": "rule",
|
| 2659 |
+
"num_demo": 1,
|
| 2660 |
+
"num_query": 15
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"name": "pictionary_genai_output_chinese",
|
| 2664 |
+
"score": 0.14285714285714285,
|
| 2665 |
+
"eval_type": "rule",
|
| 2666 |
+
"num_demo": 1,
|
| 2667 |
+
"num_query": 14
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"name": "pictionary_skribbl_io",
|
| 2671 |
+
"score": 0.2,
|
| 2672 |
+
"eval_type": "rule",
|
| 2673 |
+
"num_demo": 1,
|
| 2674 |
+
"num_query": 20
|
| 2675 |
+
},
|
| 2676 |
+
{
|
| 2677 |
+
"name": "places365_scene_type_classification",
|
| 2678 |
+
"score": 0.7142857142857143,
|
| 2679 |
+
"eval_type": "rule",
|
| 2680 |
+
"num_demo": 1,
|
| 2681 |
+
"num_query": 14
|
| 2682 |
+
},
|
| 2683 |
+
{
|
| 2684 |
+
"name": "places365_similar_scene_retrieval",
|
| 2685 |
+
"score": 0.5714285714285714,
|
| 2686 |
+
"eval_type": "rule",
|
| 2687 |
+
"num_demo": 1,
|
| 2688 |
+
"num_query": 14
|
| 2689 |
+
},
|
| 2690 |
+
{
|
| 2691 |
+
"name": "planning_screenshot_barman",
|
| 2692 |
+
"score": 0.0,
|
| 2693 |
+
"eval_type": "rule",
|
| 2694 |
+
"num_demo": 1,
|
| 2695 |
+
"num_query": 15
|
| 2696 |
+
},
|
| 2697 |
+
{
|
| 2698 |
+
"name": "planning_screenshot_blocksworld",
|
| 2699 |
+
"score": 0.0,
|
| 2700 |
+
"eval_type": "rule",
|
| 2701 |
+
"num_demo": 1,
|
| 2702 |
+
"num_query": 15
|
| 2703 |
+
},
|
| 2704 |
+
{
|
| 2705 |
+
"name": "planning_screenshot_floortile",
|
| 2706 |
+
"score": 0.0,
|
| 2707 |
+
"eval_type": "rule",
|
| 2708 |
+
"num_demo": 1,
|
| 2709 |
+
"num_query": 15
|
| 2710 |
+
},
|
| 2711 |
+
{
|
| 2712 |
+
"name": "planning_screenshot_grippers",
|
| 2713 |
+
"score": 0.0,
|
| 2714 |
+
"eval_type": "rule",
|
| 2715 |
+
"num_demo": 1,
|
| 2716 |
+
"num_query": 15
|
| 2717 |
+
},
|
| 2718 |
+
{
|
| 2719 |
+
"name": "planning_screenshot_storage",
|
| 2720 |
+
"score": 0.0,
|
| 2721 |
+
"eval_type": "rule",
|
| 2722 |
+
"num_demo": 1,
|
| 2723 |
+
"num_query": 15
|
| 2724 |
+
},
|
| 2725 |
+
{
|
| 2726 |
+
"name": "planning_screenshot_termes",
|
| 2727 |
+
"score": 0.0,
|
| 2728 |
+
"eval_type": "rule",
|
| 2729 |
+
"num_demo": 1,
|
| 2730 |
+
"num_query": 15
|
| 2731 |
+
},
|
| 2732 |
+
{
|
| 2733 |
+
"name": "planning_screenshot_tyreworld",
|
| 2734 |
+
"score": 0.0,
|
| 2735 |
+
"eval_type": "rule",
|
| 2736 |
+
"num_demo": 1,
|
| 2737 |
+
"num_query": 15
|
| 2738 |
+
},
|
| 2739 |
+
{
|
| 2740 |
+
"name": "planning_visual_barman",
|
| 2741 |
+
"score": 0.0,
|
| 2742 |
+
"eval_type": "rule",
|
| 2743 |
+
"num_demo": 1,
|
| 2744 |
+
"num_query": 15
|
| 2745 |
+
},
|
| 2746 |
+
{
|
| 2747 |
+
"name": "planning_visual_blocksworld",
|
| 2748 |
+
"score": 0.0,
|
| 2749 |
+
"eval_type": "rule",
|
| 2750 |
+
"num_demo": 1,
|
| 2751 |
+
"num_query": 15
|
| 2752 |
+
},
|
| 2753 |
+
{
|
| 2754 |
+
"name": "planning_visual_floortile",
|
| 2755 |
+
"score": 0.0,
|
| 2756 |
+
"eval_type": "rule",
|
| 2757 |
+
"num_demo": 1,
|
| 2758 |
+
"num_query": 15
|
| 2759 |
+
},
|
| 2760 |
+
{
|
| 2761 |
+
"name": "planning_visual_grippers",
|
| 2762 |
+
"score": 0.0,
|
| 2763 |
+
"eval_type": "rule",
|
| 2764 |
+
"num_demo": 1,
|
| 2765 |
+
"num_query": 15
|
| 2766 |
+
},
|
| 2767 |
+
{
|
| 2768 |
+
"name": "planning_visual_storage",
|
| 2769 |
+
"score": 0.0,
|
| 2770 |
+
"eval_type": "rule",
|
| 2771 |
+
"num_demo": 1,
|
| 2772 |
+
"num_query": 15
|
| 2773 |
+
},
|
| 2774 |
+
{
|
| 2775 |
+
"name": "planning_visual_termes",
|
| 2776 |
+
"score": 0.0,
|
| 2777 |
+
"eval_type": "rule",
|
| 2778 |
+
"num_demo": 1,
|
| 2779 |
+
"num_query": 15
|
| 2780 |
+
},
|
| 2781 |
+
{
|
| 2782 |
+
"name": "pmc_vqa_medical_image_qa",
|
| 2783 |
+
"score": 0.6842105263157895,
|
| 2784 |
+
"eval_type": "rule",
|
| 2785 |
+
"num_demo": 1,
|
| 2786 |
+
"num_query": 19
|
| 2787 |
+
},
|
| 2788 |
+
{
|
| 2789 |
+
"name": "poetry_acrostic",
|
| 2790 |
+
"score": 0.8666666666666667,
|
| 2791 |
+
"eval_type": "rule",
|
| 2792 |
+
"num_demo": 0,
|
| 2793 |
+
"num_query": 15
|
| 2794 |
+
},
|
| 2795 |
+
{
|
| 2796 |
+
"name": "poetry_acrostic_alliteration",
|
| 2797 |
+
"score": 0.06666666666666667,
|
| 2798 |
+
"eval_type": "rule",
|
| 2799 |
+
"num_demo": 0,
|
| 2800 |
+
"num_query": 15
|
| 2801 |
+
},
|
| 2802 |
+
{
|
| 2803 |
+
"name": "poetry_custom_rhyming_scheme",
|
| 2804 |
+
"score": 0.0,
|
| 2805 |
+
"eval_type": "rule",
|
| 2806 |
+
"num_demo": 0,
|
| 2807 |
+
"num_query": 15
|
| 2808 |
+
},
|
| 2809 |
+
{
|
| 2810 |
+
"name": "poetry_haiku",
|
| 2811 |
+
"score": 0.0,
|
| 2812 |
+
"eval_type": "rule",
|
| 2813 |
+
"num_demo": 0,
|
| 2814 |
+
"num_query": 15
|
| 2815 |
+
},
|
| 2816 |
+
{
|
| 2817 |
+
"name": "poetry_limerick",
|
| 2818 |
+
"score": 0.06666666666666667,
|
| 2819 |
+
"eval_type": "rule",
|
| 2820 |
+
"num_demo": 0,
|
| 2821 |
+
"num_query": 15
|
| 2822 |
+
},
|
| 2823 |
+
{
|
| 2824 |
+
"name": "poetry_petrarchian_sonnet_optional_meter",
|
| 2825 |
+
"score": 0.0,
|
| 2826 |
+
"eval_type": "rule",
|
| 2827 |
+
"num_demo": 0,
|
| 2828 |
+
"num_query": 15
|
| 2829 |
+
},
|
| 2830 |
+
{
|
| 2831 |
+
"name": "poetry_shakespearean_sonnet",
|
| 2832 |
+
"score": 0.0,
|
| 2833 |
+
"eval_type": "rule",
|
| 2834 |
+
"num_demo": 0,
|
| 2835 |
+
"num_query": 15
|
| 2836 |
+
},
|
| 2837 |
+
{
|
| 2838 |
+
"name": "pokemon_3D_recognition",
|
| 2839 |
+
"score": 0.7,
|
| 2840 |
+
"eval_type": "rule",
|
| 2841 |
+
"num_demo": 1,
|
| 2842 |
+
"num_query": 15
|
| 2843 |
+
},
|
| 2844 |
+
{
|
| 2845 |
+
"name": "polygon_interior_angles",
|
| 2846 |
+
"score": 0.05930952380952383,
|
| 2847 |
+
"eval_type": "rule",
|
| 2848 |
+
"num_demo": 1,
|
| 2849 |
+
"num_query": 14
|
| 2850 |
+
},
|
| 2851 |
+
{
|
| 2852 |
+
"name": "product_ocr_qa",
|
| 2853 |
+
"score": 0.35714285714285715,
|
| 2854 |
+
"eval_type": "rule",
|
| 2855 |
+
"num_demo": 1,
|
| 2856 |
+
"num_query": 14
|
| 2857 |
+
},
|
| 2858 |
+
{
|
| 2859 |
+
"name": "question_solution_solving",
|
| 2860 |
+
"score": 0.21428571428571427,
|
| 2861 |
+
"eval_type": "rule",
|
| 2862 |
+
"num_demo": 1,
|
| 2863 |
+
"num_query": 14
|
| 2864 |
+
},
|
| 2865 |
+
{
|
| 2866 |
+
"name": "quizlet_question_solving",
|
| 2867 |
+
"score": 0.5714285714285714,
|
| 2868 |
+
"eval_type": "rule",
|
| 2869 |
+
"num_demo": 1,
|
| 2870 |
+
"num_query": 14
|
| 2871 |
+
},
|
| 2872 |
+
{
|
| 2873 |
+
"name": "realworld_qa_en2cn",
|
| 2874 |
+
"score": 0.5,
|
| 2875 |
+
"eval_type": "rule",
|
| 2876 |
+
"num_demo": 1,
|
| 2877 |
+
"num_query": 14
|
| 2878 |
+
},
|
| 2879 |
+
{
|
| 2880 |
+
"name": "rebus",
|
| 2881 |
+
"score": 0.08695652173913043,
|
| 2882 |
+
"eval_type": "rule",
|
| 2883 |
+
"num_demo": 1,
|
| 2884 |
+
"num_query": 23
|
| 2885 |
+
},
|
| 2886 |
+
{
|
| 2887 |
+
"name": "recipe_image_ordering",
|
| 2888 |
+
"score": 0.8571428571428571,
|
| 2889 |
+
"eval_type": "rule",
|
| 2890 |
+
"num_demo": 1,
|
| 2891 |
+
"num_query": 14
|
| 2892 |
+
},
|
| 2893 |
+
{
|
| 2894 |
+
"name": "recover_masked_word_in_figure",
|
| 2895 |
+
"score": 0.35714285714285715,
|
| 2896 |
+
"eval_type": "rule",
|
| 2897 |
+
"num_demo": 1,
|
| 2898 |
+
"num_query": 14
|
| 2899 |
+
},
|
| 2900 |
+
{
|
| 2901 |
+
"name": "relative_depth_of_different_points",
|
| 2902 |
+
"score": 0.7142857142857143,
|
| 2903 |
+
"eval_type": "rule",
|
| 2904 |
+
"num_demo": 1,
|
| 2905 |
+
"num_query": 14
|
| 2906 |
+
},
|
| 2907 |
+
{
|
| 2908 |
+
"name": "relative_reflectance_of_different_regions",
|
| 2909 |
+
"score": 0.5714285714285714,
|
| 2910 |
+
"eval_type": "rule",
|
| 2911 |
+
"num_demo": 1,
|
| 2912 |
+
"num_query": 14
|
| 2913 |
+
},
|
| 2914 |
+
{
|
| 2915 |
+
"name": "remaining_playback_time_calculation",
|
| 2916 |
+
"score": 0.21428571428571427,
|
| 2917 |
+
"eval_type": "rule",
|
| 2918 |
+
"num_demo": 1,
|
| 2919 |
+
"num_query": 14
|
| 2920 |
+
},
|
| 2921 |
+
{
|
| 2922 |
+
"name": "research_website_parsing_blogpost",
|
| 2923 |
+
"score": 0.07142857142857142,
|
| 2924 |
+
"eval_type": "rule",
|
| 2925 |
+
"num_demo": 0,
|
| 2926 |
+
"num_query": 14
|
| 2927 |
+
},
|
| 2928 |
+
{
|
| 2929 |
+
"name": "research_website_parsing_homepage",
|
| 2930 |
+
"score": 0.07142857142857142,
|
| 2931 |
+
"eval_type": "rule",
|
| 2932 |
+
"num_demo": 0,
|
| 2933 |
+
"num_query": 14
|
| 2934 |
+
},
|
| 2935 |
+
{
|
| 2936 |
+
"name": "research_website_parsing_publication",
|
| 2937 |
+
"score": 0.21428571428571427,
|
| 2938 |
+
"eval_type": "rule",
|
| 2939 |
+
"num_demo": 0,
|
| 2940 |
+
"num_query": 14
|
| 2941 |
+
},
|
| 2942 |
+
{
|
| 2943 |
+
"name": "reward_models_i2t_reward",
|
| 2944 |
+
"score": 0.6428571428571429,
|
| 2945 |
+
"eval_type": "rule",
|
| 2946 |
+
"num_demo": 1,
|
| 2947 |
+
"num_query": 14
|
| 2948 |
+
},
|
| 2949 |
+
{
|
| 2950 |
+
"name": "reward_models_t2i_reward",
|
| 2951 |
+
"score": 0.5,
|
| 2952 |
+
"eval_type": "rule",
|
| 2953 |
+
"num_demo": 1,
|
| 2954 |
+
"num_query": 14
|
| 2955 |
+
},
|
| 2956 |
+
{
|
| 2957 |
+
"name": "road_map_find_highway_between_two_place",
|
| 2958 |
+
"score": 0.6470588235294118,
|
| 2959 |
+
"eval_type": "rule",
|
| 2960 |
+
"num_demo": 1,
|
| 2961 |
+
"num_query": 17
|
| 2962 |
+
},
|
| 2963 |
+
{
|
| 2964 |
+
"name": "rocks_samples_compare",
|
| 2965 |
+
"score": 0.42857142857142855,
|
| 2966 |
+
"eval_type": "rule",
|
| 2967 |
+
"num_demo": 1,
|
| 2968 |
+
"num_query": 14
|
| 2969 |
+
},
|
| 2970 |
+
{
|
| 2971 |
+
"name": "rocks_samples_identify",
|
| 2972 |
+
"score": 0.2,
|
| 2973 |
+
"eval_type": "rule",
|
| 2974 |
+
"num_demo": 1,
|
| 2975 |
+
"num_query": 15
|
| 2976 |
+
},
|
| 2977 |
+
{
|
| 2978 |
+
"name": "scibench_calculus_wo_solution",
|
| 2979 |
+
"score": 0.30612244897959184,
|
| 2980 |
+
"eval_type": "rule",
|
| 2981 |
+
"num_demo": 1,
|
| 2982 |
+
"num_query": 49
|
| 2983 |
+
},
|
| 2984 |
+
{
|
| 2985 |
+
"name": "scibench_fundamental_wo_solution",
|
| 2986 |
+
"score": 0.3673469387755102,
|
| 2987 |
+
"eval_type": "rule",
|
| 2988 |
+
"num_demo": 1,
|
| 2989 |
+
"num_query": 49
|
| 2990 |
+
},
|
| 2991 |
+
{
|
| 2992 |
+
"name": "science_basic_physics",
|
| 2993 |
+
"score": 0.8666666666666667,
|
| 2994 |
+
"eval_type": "rule",
|
| 2995 |
+
"num_demo": 1,
|
| 2996 |
+
"num_query": 15
|
| 2997 |
+
},
|
| 2998 |
+
{
|
| 2999 |
+
"name": "science_molecule_chemistry",
|
| 3000 |
+
"score": 0.8,
|
| 3001 |
+
"eval_type": "rule",
|
| 3002 |
+
"num_demo": 1,
|
| 3003 |
+
"num_query": 15
|
| 3004 |
+
},
|
| 3005 |
+
{
|
| 3006 |
+
"name": "screenshot_lighteval_math",
|
| 3007 |
+
"score": 0.6,
|
| 3008 |
+
"eval_type": "rule",
|
| 3009 |
+
"num_demo": 1,
|
| 3010 |
+
"num_query": 15
|
| 3011 |
+
},
|
| 3012 |
+
{
|
| 3013 |
+
"name": "screenshot_theoremqa",
|
| 3014 |
+
"score": 0.7142857142857143,
|
| 3015 |
+
"eval_type": "rule",
|
| 3016 |
+
"num_demo": 1,
|
| 3017 |
+
"num_query": 14
|
| 3018 |
+
},
|
| 3019 |
+
{
|
| 3020 |
+
"name": "semantic_matching_of_two_images",
|
| 3021 |
+
"score": 0.6428571428571429,
|
| 3022 |
+
"eval_type": "rule",
|
| 3023 |
+
"num_demo": 1,
|
| 3024 |
+
"num_query": 14
|
| 3025 |
+
},
|
| 3026 |
+
{
|
| 3027 |
+
"name": "shape_composition_colours",
|
| 3028 |
+
"score": 0.12698412698412698,
|
| 3029 |
+
"eval_type": "rule",
|
| 3030 |
+
"num_demo": 1,
|
| 3031 |
+
"num_query": 14
|
| 3032 |
+
},
|
| 3033 |
+
{
|
| 3034 |
+
"name": "shape_composition_shapes",
|
| 3035 |
+
"score": 0.14285714285714285,
|
| 3036 |
+
"eval_type": "rule",
|
| 3037 |
+
"num_demo": 1,
|
| 3038 |
+
"num_query": 14
|
| 3039 |
+
},
|
| 3040 |
+
{
|
| 3041 |
+
"name": "sign_language",
|
| 3042 |
+
"score": 0.07142857142857142,
|
| 3043 |
+
"eval_type": "rule",
|
| 3044 |
+
"num_demo": 1,
|
| 3045 |
+
"num_query": 14
|
| 3046 |
+
},
|
| 3047 |
+
{
|
| 3048 |
+
"name": "signage_navigation",
|
| 3049 |
+
"score": 0.7857142857142857,
|
| 3050 |
+
"eval_type": "rule",
|
| 3051 |
+
"num_demo": 1,
|
| 3052 |
+
"num_query": 14
|
| 3053 |
+
},
|
| 3054 |
+
{
|
| 3055 |
+
"name": "signboard_identification",
|
| 3056 |
+
"score": 0.5714285714285714,
|
| 3057 |
+
"eval_type": "rule",
|
| 3058 |
+
"num_demo": 1,
|
| 3059 |
+
"num_query": 14
|
| 3060 |
+
},
|
| 3061 |
+
{
|
| 3062 |
+
"name": "single_person_pose_estimation",
|
| 3063 |
+
"score": 0.3191040111385921,
|
| 3064 |
+
"eval_type": "rule",
|
| 3065 |
+
"num_demo": 1,
|
| 3066 |
+
"num_query": 14
|
| 3067 |
+
},
|
| 3068 |
+
{
|
| 3069 |
+
"name": "snli_ve_visual_entailment",
|
| 3070 |
+
"score": 0.8,
|
| 3071 |
+
"eval_type": "rule",
|
| 3072 |
+
"num_demo": 1,
|
| 3073 |
+
"num_query": 15
|
| 3074 |
+
},
|
| 3075 |
+
{
|
| 3076 |
+
"name": "soccer_offside",
|
| 3077 |
+
"score": 0.3333333333333333,
|
| 3078 |
+
"eval_type": "rule",
|
| 3079 |
+
"num_demo": 1,
|
| 3080 |
+
"num_query": 9
|
| 3081 |
+
},
|
| 3082 |
+
{
|
| 3083 |
+
"name": "song_title_identification_from_lyrics",
|
| 3084 |
+
"score": 0.32142857142857145,
|
| 3085 |
+
"eval_type": "rule",
|
| 3086 |
+
"num_demo": 1,
|
| 3087 |
+
"num_query": 14
|
| 3088 |
+
},
|
| 3089 |
+
{
|
| 3090 |
+
"name": "sta_action_localization_video",
|
| 3091 |
+
"score": 0.4375,
|
| 3092 |
+
"eval_type": "rule",
|
| 3093 |
+
"num_demo": 1,
|
| 3094 |
+
"num_query": 16
|
| 3095 |
+
},
|
| 3096 |
+
{
|
| 3097 |
+
"name": "stackoverflow_debug_QA",
|
| 3098 |
+
"score": 0.6904761904761905,
|
| 3099 |
+
"eval_type": "rule",
|
| 3100 |
+
"num_demo": 1,
|
| 3101 |
+
"num_query": 14
|
| 3102 |
+
},
|
| 3103 |
+
{
|
| 3104 |
+
"name": "star_object_interaction_video",
|
| 3105 |
+
"score": 0.625,
|
| 3106 |
+
"eval_type": "rule",
|
| 3107 |
+
"num_demo": 1,
|
| 3108 |
+
"num_query": 16
|
| 3109 |
+
},
|
| 3110 |
+
{
|
| 3111 |
+
"name": "stock_info_parsing",
|
| 3112 |
+
"score": 0.9747899159663866,
|
| 3113 |
+
"eval_type": "rule",
|
| 3114 |
+
"num_demo": 1,
|
| 3115 |
+
"num_query": 14
|
| 3116 |
+
},
|
| 3117 |
+
{
|
| 3118 |
+
"name": "stock_info_retrieval",
|
| 3119 |
+
"score": 0.2857142857142857,
|
| 3120 |
+
"eval_type": "rule",
|
| 3121 |
+
"num_demo": 0,
|
| 3122 |
+
"num_query": 14
|
| 3123 |
+
},
|
| 3124 |
+
{
|
| 3125 |
+
"name": "stock_price_future_prediction",
|
| 3126 |
+
"score": 0.8110714285714286,
|
| 3127 |
+
"eval_type": "rule",
|
| 3128 |
+
"num_demo": 1,
|
| 3129 |
+
"num_query": 14
|
| 3130 |
+
},
|
| 3131 |
+
{
|
| 3132 |
+
"name": "super_clevr_scene_understanding",
|
| 3133 |
+
"score": 0.6428571428571429,
|
| 3134 |
+
"eval_type": "rule",
|
| 3135 |
+
"num_demo": 1,
|
| 3136 |
+
"num_query": 14
|
| 3137 |
+
},
|
| 3138 |
+
{
|
| 3139 |
+
"name": "symbolic_graphics_programs_computer_aided_design",
|
| 3140 |
+
"score": 0.2857142857142857,
|
| 3141 |
+
"eval_type": "rule",
|
| 3142 |
+
"num_demo": 1,
|
| 3143 |
+
"num_query": 14
|
| 3144 |
+
},
|
| 3145 |
+
{
|
| 3146 |
+
"name": "symbolic_graphics_programs_scalable_vector_graphics",
|
| 3147 |
+
"score": 0.16666666666666666,
|
| 3148 |
+
"eval_type": "rule",
|
| 3149 |
+
"num_demo": 1,
|
| 3150 |
+
"num_query": 18
|
| 3151 |
+
},
|
| 3152 |
+
{
|
| 3153 |
+
"name": "table_understanding_complex_question_answering",
|
| 3154 |
+
"score": 0.5714285714285714,
|
| 3155 |
+
"eval_type": "rule",
|
| 3156 |
+
"num_demo": 1,
|
| 3157 |
+
"num_query": 14
|
| 3158 |
+
},
|
| 3159 |
+
{
|
| 3160 |
+
"name": "table_understanding_fact_verification",
|
| 3161 |
+
"score": 0.9285714285714286,
|
| 3162 |
+
"eval_type": "rule",
|
| 3163 |
+
"num_demo": 1,
|
| 3164 |
+
"num_query": 14
|
| 3165 |
+
},
|
| 3166 |
+
{
|
| 3167 |
+
"name": "text_entity_replace",
|
| 3168 |
+
"score": 0.7142857142857143,
|
| 3169 |
+
"eval_type": "rule",
|
| 3170 |
+
"num_demo": 1,
|
| 3171 |
+
"num_query": 14
|
| 3172 |
+
},
|
| 3173 |
+
{
|
| 3174 |
+
"name": "text_style",
|
| 3175 |
+
"score": 0.5,
|
| 3176 |
+
"eval_type": "rule",
|
| 3177 |
+
"num_demo": 1,
|
| 3178 |
+
"num_query": 14
|
| 3179 |
+
},
|
| 3180 |
+
{
|
| 3181 |
+
"name": "top_rated_hotel_identification",
|
| 3182 |
+
"score": 0.8571428571428571,
|
| 3183 |
+
"eval_type": "rule",
|
| 3184 |
+
"num_demo": 1,
|
| 3185 |
+
"num_query": 14
|
| 3186 |
+
},
|
| 3187 |
+
{
|
| 3188 |
+
"name": "top_video_creator_identification",
|
| 3189 |
+
"score": 0.6428571428571429,
|
| 3190 |
+
"eval_type": "rule",
|
| 3191 |
+
"num_demo": 1,
|
| 3192 |
+
"num_query": 14
|
| 3193 |
+
},
|
| 3194 |
+
{
|
| 3195 |
+
"name": "topological_sort",
|
| 3196 |
+
"score": 0.0,
|
| 3197 |
+
"eval_type": "rule",
|
| 3198 |
+
"num_demo": 1,
|
| 3199 |
+
"num_query": 14
|
| 3200 |
+
},
|
| 3201 |
+
{
|
| 3202 |
+
"name": "tqa_textbook_qa",
|
| 3203 |
+
"score": 0.9285714285714286,
|
| 3204 |
+
"eval_type": "rule",
|
| 3205 |
+
"num_demo": 1,
|
| 3206 |
+
"num_query": 14
|
| 3207 |
+
},
|
| 3208 |
+
{
|
| 3209 |
+
"name": "traffic_future_prediction_from_line_plot",
|
| 3210 |
+
"score": 0.7814210526315792,
|
| 3211 |
+
"eval_type": "rule",
|
| 3212 |
+
"num_demo": 1,
|
| 3213 |
+
"num_query": 19
|
| 3214 |
+
},
|
| 3215 |
+
{
|
| 3216 |
+
"name": "transit_map_intersection_points",
|
| 3217 |
+
"score": 0.555952380952381,
|
| 3218 |
+
"eval_type": "rule",
|
| 3219 |
+
"num_demo": 1,
|
| 3220 |
+
"num_query": 14
|
| 3221 |
+
},
|
| 3222 |
+
{
|
| 3223 |
+
"name": "tv_show_retrieval_by_character",
|
| 3224 |
+
"score": 0.7857142857142857,
|
| 3225 |
+
"eval_type": "rule",
|
| 3226 |
+
"num_demo": 0,
|
| 3227 |
+
"num_query": 14
|
| 3228 |
+
},
|
| 3229 |
+
{
|
| 3230 |
+
"name": "veracity",
|
| 3231 |
+
"score": 0.7857142857142857,
|
| 3232 |
+
"eval_type": "rule",
|
| 3233 |
+
"num_demo": 1,
|
| 3234 |
+
"num_query": 14
|
| 3235 |
+
},
|
| 3236 |
+
{
|
| 3237 |
+
"name": "vibe_eval_open",
|
| 3238 |
+
"score": 0.35714285714285715,
|
| 3239 |
+
"eval_type": "rule",
|
| 3240 |
+
"num_demo": 1,
|
| 3241 |
+
"num_query": 14
|
| 3242 |
+
},
|
| 3243 |
+
{
|
| 3244 |
+
"name": "video_action_recognition",
|
| 3245 |
+
"score": 0.8214285714285714,
|
| 3246 |
+
"eval_type": "rule",
|
| 3247 |
+
"num_demo": 1,
|
| 3248 |
+
"num_query": 14
|
| 3249 |
+
},
|
| 3250 |
+
{
|
| 3251 |
+
"name": "video_camera_motion_description",
|
| 3252 |
+
"score": 0.21428571428571427,
|
| 3253 |
+
"eval_type": "rule",
|
| 3254 |
+
"num_demo": 1,
|
| 3255 |
+
"num_query": 14
|
| 3256 |
+
},
|
| 3257 |
+
{
|
| 3258 |
+
"name": "video_content_reasoning",
|
| 3259 |
+
"score": 0.3333333333333333,
|
| 3260 |
+
"eval_type": "rule",
|
| 3261 |
+
"num_demo": 1,
|
| 3262 |
+
"num_query": 9
|
| 3263 |
+
},
|
| 3264 |
+
{
|
| 3265 |
+
"name": "video_eval_dynamic_pref",
|
| 3266 |
+
"score": 0.0,
|
| 3267 |
+
"eval_type": "rule",
|
| 3268 |
+
"num_demo": 1,
|
| 3269 |
+
"num_query": 16
|
| 3270 |
+
},
|
| 3271 |
+
{
|
| 3272 |
+
"name": "video_eval_factual_pref",
|
| 3273 |
+
"score": 0.0,
|
| 3274 |
+
"eval_type": "rule",
|
| 3275 |
+
"num_demo": 1,
|
| 3276 |
+
"num_query": 14
|
| 3277 |
+
},
|
| 3278 |
+
{
|
| 3279 |
+
"name": "video_eval_visual_pref",
|
| 3280 |
+
"score": 0.0,
|
| 3281 |
+
"eval_type": "rule",
|
| 3282 |
+
"num_demo": 1,
|
| 3283 |
+
"num_query": 16
|
| 3284 |
+
},
|
| 3285 |
+
{
|
| 3286 |
+
"name": "video_grounding_spatial",
|
| 3287 |
+
"score": 0.35714285714285715,
|
| 3288 |
+
"eval_type": "rule",
|
| 3289 |
+
"num_demo": 1,
|
| 3290 |
+
"num_query": 14
|
| 3291 |
+
},
|
| 3292 |
+
{
|
| 3293 |
+
"name": "video_grounding_temporal",
|
| 3294 |
+
"score": 0.2,
|
| 3295 |
+
"eval_type": "rule",
|
| 3296 |
+
"num_demo": 1,
|
| 3297 |
+
"num_query": 15
|
| 3298 |
+
},
|
| 3299 |
+
{
|
| 3300 |
+
"name": "video_intent_recognition",
|
| 3301 |
+
"score": 0.6428571428571429,
|
| 3302 |
+
"eval_type": "rule",
|
| 3303 |
+
"num_demo": 1,
|
| 3304 |
+
"num_query": 14
|
| 3305 |
+
},
|
| 3306 |
+
{
|
| 3307 |
+
"name": "video_motion_matching_3D_real",
|
| 3308 |
+
"score": 0.26666666666666666,
|
| 3309 |
+
"eval_type": "rule",
|
| 3310 |
+
"num_demo": 1,
|
| 3311 |
+
"num_query": 15
|
| 3312 |
+
},
|
| 3313 |
+
{
|
| 3314 |
+
"name": "video_motion_matching_real_3D",
|
| 3315 |
+
"score": 0.21428571428571427,
|
| 3316 |
+
"eval_type": "rule",
|
| 3317 |
+
"num_demo": 1,
|
| 3318 |
+
"num_query": 14
|
| 3319 |
+
},
|
| 3320 |
+
{
|
| 3321 |
+
"name": "video_segments_reordering",
|
| 3322 |
+
"score": 0.14285714285714285,
|
| 3323 |
+
"eval_type": "rule",
|
| 3324 |
+
"num_demo": 1,
|
| 3325 |
+
"num_query": 14
|
| 3326 |
+
},
|
| 3327 |
+
{
|
| 3328 |
+
"name": "video_to_camera_trajectory_retrieval",
|
| 3329 |
+
"score": 0.0,
|
| 3330 |
+
"eval_type": "rule",
|
| 3331 |
+
"num_demo": 1,
|
| 3332 |
+
"num_query": 14
|
| 3333 |
+
},
|
| 3334 |
+
{
|
| 3335 |
+
"name": "visual_correspondance_in_two_images",
|
| 3336 |
+
"score": 0.7857142857142857,
|
| 3337 |
+
"eval_type": "rule",
|
| 3338 |
+
"num_demo": 1,
|
| 3339 |
+
"num_query": 14
|
| 3340 |
+
},
|
| 3341 |
+
{
|
| 3342 |
+
"name": "visual_dialog_image_guessing",
|
| 3343 |
+
"score": 0.9333333333333333,
|
| 3344 |
+
"eval_type": "rule",
|
| 3345 |
+
"num_demo": 0,
|
| 3346 |
+
"num_query": 15
|
| 3347 |
+
},
|
| 3348 |
+
{
|
| 3349 |
+
"name": "visual_prediction_rater_3d_assembled_quality_understanding",
|
| 3350 |
+
"score": 0.35714285714285715,
|
| 3351 |
+
"eval_type": "rule",
|
| 3352 |
+
"num_demo": 1,
|
| 3353 |
+
"num_query": 14
|
| 3354 |
+
},
|
| 3355 |
+
{
|
| 3356 |
+
"name": "visual_prediction_rater_depth_estimation",
|
| 3357 |
+
"score": 0.21428571428571427,
|
| 3358 |
+
"eval_type": "rule",
|
| 3359 |
+
"num_demo": 1,
|
| 3360 |
+
"num_query": 14
|
| 3361 |
+
},
|
| 3362 |
+
{
|
| 3363 |
+
"name": "visual_prediction_rater_novel_view_synthesis",
|
| 3364 |
+
"score": 0.21428571428571427,
|
| 3365 |
+
"eval_type": "rule",
|
| 3366 |
+
"num_demo": 1,
|
| 3367 |
+
"num_query": 14
|
| 3368 |
+
},
|
| 3369 |
+
{
|
| 3370 |
+
"name": "visual_prediction_rater_openable_part_segmentation",
|
| 3371 |
+
"score": 0.0,
|
| 3372 |
+
"eval_type": "rule",
|
| 3373 |
+
"num_demo": 1,
|
| 3374 |
+
"num_query": 14
|
| 3375 |
+
},
|
| 3376 |
+
{
|
| 3377 |
+
"name": "visual_prediction_rater_panoptic_segmentation",
|
| 3378 |
+
"score": 0.07142857142857142,
|
| 3379 |
+
"eval_type": "rule",
|
| 3380 |
+
"num_demo": 1,
|
| 3381 |
+
"num_query": 14
|
| 3382 |
+
},
|
| 3383 |
+
{
|
| 3384 |
+
"name": "visual_prediction_rater_plane_segmentation",
|
| 3385 |
+
"score": 0.4222222222222222,
|
| 3386 |
+
"eval_type": "rule",
|
| 3387 |
+
"num_demo": 1,
|
| 3388 |
+
"num_query": 15
|
| 3389 |
+
},
|
| 3390 |
+
{
|
| 3391 |
+
"name": "visual_prediction_rater_semantic_segmentation",
|
| 3392 |
+
"score": 0.5208333333333333,
|
| 3393 |
+
"eval_type": "rule",
|
| 3394 |
+
"num_demo": 1,
|
| 3395 |
+
"num_query": 16
|
| 3396 |
+
},
|
| 3397 |
+
{
|
| 3398 |
+
"name": "visual_prediction_rater_surface_normal_estimation",
|
| 3399 |
+
"score": 0.5952380952380952,
|
| 3400 |
+
"eval_type": "rule",
|
| 3401 |
+
"num_demo": 1,
|
| 3402 |
+
"num_query": 14
|
| 3403 |
+
},
|
| 3404 |
+
{
|
| 3405 |
+
"name": "vizwiz_quality_accessment_for_blind",
|
| 3406 |
+
"score": 0.21428571428571427,
|
| 3407 |
+
"eval_type": "rule",
|
| 3408 |
+
"num_demo": 1,
|
| 3409 |
+
"num_query": 14
|
| 3410 |
+
},
|
| 3411 |
+
{
|
| 3412 |
+
"name": "vln_english_next_step",
|
| 3413 |
+
"score": 0.3333333333333333,
|
| 3414 |
+
"eval_type": "rule",
|
| 3415 |
+
"num_demo": 1,
|
| 3416 |
+
"num_query": 15
|
| 3417 |
+
},
|
| 3418 |
+
{
|
| 3419 |
+
"name": "vln_hindi_next_step",
|
| 3420 |
+
"score": 0.0,
|
| 3421 |
+
"eval_type": "rule",
|
| 3422 |
+
"num_demo": 1,
|
| 3423 |
+
"num_query": 15
|
| 3424 |
+
},
|
| 3425 |
+
{
|
| 3426 |
+
"name": "vln_identify_location",
|
| 3427 |
+
"score": 0.14545454545454545,
|
| 3428 |
+
"eval_type": "rule",
|
| 3429 |
+
"num_demo": 1,
|
| 3430 |
+
"num_query": 15
|
| 3431 |
+
},
|
| 3432 |
+
{
|
| 3433 |
+
"name": "vln_identify_robot",
|
| 3434 |
+
"score": 0.4666666666666667,
|
| 3435 |
+
"eval_type": "rule",
|
| 3436 |
+
"num_demo": 0,
|
| 3437 |
+
"num_query": 15
|
| 3438 |
+
},
|
| 3439 |
+
{
|
| 3440 |
+
"name": "vln_tegulu_next_step",
|
| 3441 |
+
"score": 0.26666666666666666,
|
| 3442 |
+
"eval_type": "rule",
|
| 3443 |
+
"num_demo": 1,
|
| 3444 |
+
"num_query": 15
|
| 3445 |
+
},
|
| 3446 |
+
{
|
| 3447 |
+
"name": "vlnqa_egocentric_navigation_video",
|
| 3448 |
+
"score": 0.3125,
|
| 3449 |
+
"eval_type": "rule",
|
| 3450 |
+
"num_demo": 1,
|
| 3451 |
+
"num_query": 16
|
| 3452 |
+
},
|
| 3453 |
+
{
|
| 3454 |
+
"name": "waldo",
|
| 3455 |
+
"score": 0.0,
|
| 3456 |
+
"eval_type": "rule",
|
| 3457 |
+
"num_demo": 1,
|
| 3458 |
+
"num_query": 18
|
| 3459 |
+
},
|
| 3460 |
+
{
|
| 3461 |
+
"name": "waybill_number_sequence_extraction",
|
| 3462 |
+
"score": 0.5714285714285714,
|
| 3463 |
+
"eval_type": "rule",
|
| 3464 |
+
"num_demo": 1,
|
| 3465 |
+
"num_query": 14
|
| 3466 |
+
},
|
| 3467 |
+
{
|
| 3468 |
+
"name": "weather_info_parsing",
|
| 3469 |
+
"score": 0.8968253968253969,
|
| 3470 |
+
"eval_type": "rule",
|
| 3471 |
+
"num_demo": 1,
|
| 3472 |
+
"num_query": 14
|
| 3473 |
+
},
|
| 3474 |
+
{
|
| 3475 |
+
"name": "weather_info_retrieval",
|
| 3476 |
+
"score": 0.14285714285714285,
|
| 3477 |
+
"eval_type": "rule",
|
| 3478 |
+
"num_demo": 0,
|
| 3479 |
+
"num_query": 14
|
| 3480 |
+
},
|
| 3481 |
+
{
|
| 3482 |
+
"name": "weather_map_climate_type_temperature_parsing",
|
| 3483 |
+
"score": 0.5,
|
| 3484 |
+
"eval_type": "rule",
|
| 3485 |
+
"num_demo": 1,
|
| 3486 |
+
"num_query": 14
|
| 3487 |
+
},
|
| 3488 |
+
{
|
| 3489 |
+
"name": "web_action_grounding",
|
| 3490 |
+
"score": 0.7857142857142857,
|
| 3491 |
+
"eval_type": "rule",
|
| 3492 |
+
"num_demo": 1,
|
| 3493 |
+
"num_query": 14
|
| 3494 |
+
},
|
| 3495 |
+
{
|
| 3496 |
+
"name": "web_action_prediction",
|
| 3497 |
+
"score": 0.7857142857142857,
|
| 3498 |
+
"eval_type": "rule",
|
| 3499 |
+
"num_demo": 1,
|
| 3500 |
+
"num_query": 14
|
| 3501 |
+
},
|
| 3502 |
+
{
|
| 3503 |
+
"name": "webpage_code_understanding",
|
| 3504 |
+
"score": 0.5555555555555556,
|
| 3505 |
+
"eval_type": "rule",
|
| 3506 |
+
"num_demo": 1,
|
| 3507 |
+
"num_query": 9
|
| 3508 |
+
},
|
| 3509 |
+
{
|
| 3510 |
+
"name": "widerface_face_count_and_event_classification",
|
| 3511 |
+
"score": 0.6785714285714286,
|
| 3512 |
+
"eval_type": "rule",
|
| 3513 |
+
"num_demo": 1,
|
| 3514 |
+
"num_query": 14
|
| 3515 |
+
},
|
| 3516 |
+
{
|
| 3517 |
+
"name": "worldle",
|
| 3518 |
+
"score": 0.1642857142857143,
|
| 3519 |
+
"eval_type": "rule",
|
| 3520 |
+
"num_demo": 1,
|
| 3521 |
+
"num_query": 14
|
| 3522 |
+
},
|
| 3523 |
+
{
|
| 3524 |
+
"name": "xor_images",
|
| 3525 |
+
"score": 0.3333333333333333,
|
| 3526 |
+
"eval_type": "rule",
|
| 3527 |
+
"num_demo": 0,
|
| 3528 |
+
"num_query": 15
|
| 3529 |
+
},
|
| 3530 |
+
{
|
| 3531 |
+
"name": "youtube_video_info_parsing",
|
| 3532 |
+
"score": 0.75,
|
| 3533 |
+
"eval_type": "rule",
|
| 3534 |
+
"num_demo": 1,
|
| 3535 |
+
"num_query": 14
|
| 3536 |
+
}
|
| 3537 |
+
]
|