Spaces:
Running
Running
Upload ALICE series on MMEB-V1 scores.
#131
by lcxrocks - opened
- scores/ALICE-2B.json +243 -0
- scores/ALICE-3B.json +243 -0
- scores/ALICE-4B.json +243 -0
- scores/ALICE-7B.json +243 -0
- scores/ALICE-8B.json +243 -0
scores/ALICE-2B.json
ADDED
|
@@ -0,0 +1,243 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"model_name": "ALICE-2B",
|
| 4 |
+
"model_backbone": "Qwen3VL-2B",
|
| 5 |
+
"model_size": "2B parameters",
|
| 6 |
+
"embedding_dimension": null,
|
| 7 |
+
"max_length_tokens": null,
|
| 8 |
+
"model_release_date": "2026-5-11",
|
| 9 |
+
"data_source": "Self-Reported",
|
| 10 |
+
"url": null,
|
| 11 |
+
"report_generated_date": "2026-05-11T16:17:05.653050"
|
| 12 |
+
},
|
| 13 |
+
"metrics": {
|
| 14 |
+
"image": {
|
| 15 |
+
"ImageNet-1K": {
|
| 16 |
+
"acc": 0.834,
|
| 17 |
+
"num_correct": 834,
|
| 18 |
+
"num_pred": 1000
|
| 19 |
+
},
|
| 20 |
+
"N24News": {
|
| 21 |
+
"acc": 0.796,
|
| 22 |
+
"num_correct": 796,
|
| 23 |
+
"num_pred": 1000
|
| 24 |
+
},
|
| 25 |
+
"HatefulMemes": {
|
| 26 |
+
"acc": 0.7,
|
| 27 |
+
"num_correct": 700,
|
| 28 |
+
"num_pred": 1000
|
| 29 |
+
},
|
| 30 |
+
"VOC2007": {
|
| 31 |
+
"acc": 0.915,
|
| 32 |
+
"num_correct": 915,
|
| 33 |
+
"num_pred": 1000
|
| 34 |
+
},
|
| 35 |
+
"SUN397": {
|
| 36 |
+
"acc": 0.806,
|
| 37 |
+
"num_correct": 806,
|
| 38 |
+
"num_pred": 1000
|
| 39 |
+
},
|
| 40 |
+
"Place365": {
|
| 41 |
+
"acc": 0.475,
|
| 42 |
+
"num_correct": 475,
|
| 43 |
+
"num_pred": 1000
|
| 44 |
+
},
|
| 45 |
+
"ImageNet-A": {
|
| 46 |
+
"acc": 0.528,
|
| 47 |
+
"num_correct": 528,
|
| 48 |
+
"num_pred": 1000
|
| 49 |
+
},
|
| 50 |
+
"ImageNet-R": {
|
| 51 |
+
"acc": 0.891,
|
| 52 |
+
"num_correct": 891,
|
| 53 |
+
"num_pred": 1000
|
| 54 |
+
},
|
| 55 |
+
"ObjectNet": {
|
| 56 |
+
"acc": 0.741,
|
| 57 |
+
"num_correct": 741,
|
| 58 |
+
"num_pred": 1000
|
| 59 |
+
},
|
| 60 |
+
"Country211": {
|
| 61 |
+
"acc": 0.184,
|
| 62 |
+
"num_correct": 184,
|
| 63 |
+
"num_pred": 1000
|
| 64 |
+
},
|
| 65 |
+
"OK-VQA": {
|
| 66 |
+
"acc": 0.674,
|
| 67 |
+
"num_correct": 674,
|
| 68 |
+
"num_pred": 1000
|
| 69 |
+
},
|
| 70 |
+
"A-OKVQA": {
|
| 71 |
+
"acc": 0.577,
|
| 72 |
+
"num_correct": 577,
|
| 73 |
+
"num_pred": 1000
|
| 74 |
+
},
|
| 75 |
+
"DocVQA": {
|
| 76 |
+
"acc": 0.919,
|
| 77 |
+
"num_correct": 919,
|
| 78 |
+
"num_pred": 1000
|
| 79 |
+
},
|
| 80 |
+
"InfographicsVQA": {
|
| 81 |
+
"acc": 0.673,
|
| 82 |
+
"num_correct": 673,
|
| 83 |
+
"num_pred": 1000
|
| 84 |
+
},
|
| 85 |
+
"ChartQA": {
|
| 86 |
+
"acc": 0.631,
|
| 87 |
+
"num_correct": 631,
|
| 88 |
+
"num_pred": 1000
|
| 89 |
+
},
|
| 90 |
+
"Visual7W": {
|
| 91 |
+
"acc": 0.548,
|
| 92 |
+
"num_correct": 548,
|
| 93 |
+
"num_pred": 1000
|
| 94 |
+
},
|
| 95 |
+
"ScienceQA": {
|
| 96 |
+
"acc": 0.458,
|
| 97 |
+
"num_correct": 458,
|
| 98 |
+
"num_pred": 1000
|
| 99 |
+
},
|
| 100 |
+
"VizWiz": {
|
| 101 |
+
"acc": 0.481,
|
| 102 |
+
"num_correct": 481,
|
| 103 |
+
"num_pred": 1000
|
| 104 |
+
},
|
| 105 |
+
"GQA": {
|
| 106 |
+
"acc": 0.703,
|
| 107 |
+
"num_correct": 703,
|
| 108 |
+
"num_pred": 1000
|
| 109 |
+
},
|
| 110 |
+
"TextVQA": {
|
| 111 |
+
"acc": 0.801,
|
| 112 |
+
"num_correct": 801,
|
| 113 |
+
"num_pred": 1000
|
| 114 |
+
},
|
| 115 |
+
"VisDial": {
|
| 116 |
+
"acc": 0.845,
|
| 117 |
+
"num_correct": 845,
|
| 118 |
+
"num_pred": 1000
|
| 119 |
+
},
|
| 120 |
+
"CIRR": {
|
| 121 |
+
"acc": 0.585,
|
| 122 |
+
"num_correct": 585,
|
| 123 |
+
"num_pred": 1000
|
| 124 |
+
},
|
| 125 |
+
"VisualNews_t2i": {
|
| 126 |
+
"acc": 0.74,
|
| 127 |
+
"num_correct": 740,
|
| 128 |
+
"num_pred": 1000
|
| 129 |
+
},
|
| 130 |
+
"VisualNews_i2t": {
|
| 131 |
+
"acc": 0.768,
|
| 132 |
+
"num_correct": 768,
|
| 133 |
+
"num_pred": 1000
|
| 134 |
+
},
|
| 135 |
+
"MSCOCO_t2i": {
|
| 136 |
+
"acc": 0.79,
|
| 137 |
+
"num_correct": 790,
|
| 138 |
+
"num_pred": 1000
|
| 139 |
+
},
|
| 140 |
+
"MSCOCO_i2t": {
|
| 141 |
+
"acc": 0.763,
|
| 142 |
+
"num_correct": 763,
|
| 143 |
+
"num_pred": 1000
|
| 144 |
+
},
|
| 145 |
+
"NIGHTS": {
|
| 146 |
+
"acc": 0.664,
|
| 147 |
+
"num_correct": 664,
|
| 148 |
+
"num_pred": 1000
|
| 149 |
+
},
|
| 150 |
+
"WebQA": {
|
| 151 |
+
"acc": 0.882,
|
| 152 |
+
"num_correct": 882,
|
| 153 |
+
"num_pred": 1000
|
| 154 |
+
},
|
| 155 |
+
"FashionIQ": {
|
| 156 |
+
"acc": 0.272,
|
| 157 |
+
"num_correct": 272,
|
| 158 |
+
"num_pred": 1000
|
| 159 |
+
},
|
| 160 |
+
"Wiki-SS-NQ": {
|
| 161 |
+
"acc": 0.633,
|
| 162 |
+
"num_correct": 633,
|
| 163 |
+
"num_pred": 1000
|
| 164 |
+
},
|
| 165 |
+
"OVEN": {
|
| 166 |
+
"acc": 0.621,
|
| 167 |
+
"num_correct": 621,
|
| 168 |
+
"num_pred": 1000
|
| 169 |
+
},
|
| 170 |
+
"EDIS": {
|
| 171 |
+
"acc": 0.893,
|
| 172 |
+
"num_correct": 893,
|
| 173 |
+
"num_pred": 1000
|
| 174 |
+
},
|
| 175 |
+
"MSCOCO": {
|
| 176 |
+
"acc": 0.921,
|
| 177 |
+
"num_correct": 921,
|
| 178 |
+
"num_pred": 1000
|
| 179 |
+
},
|
| 180 |
+
"RefCOCO": {
|
| 181 |
+
"acc": 0.939,
|
| 182 |
+
"num_correct": 939,
|
| 183 |
+
"num_pred": 1000
|
| 184 |
+
},
|
| 185 |
+
"RefCOCO-Matching": {
|
| 186 |
+
"acc": 0.901,
|
| 187 |
+
"num_correct": 901,
|
| 188 |
+
"num_pred": 1000
|
| 189 |
+
},
|
| 190 |
+
"Visual7W-Pointing": {
|
| 191 |
+
"acc": 0.861,
|
| 192 |
+
"num_correct": 861,
|
| 193 |
+
"num_pred": 1000
|
| 194 |
+
}
|
| 195 |
+
},
|
| 196 |
+
"video": {
|
| 197 |
+
"K700": "DIR_N/A",
|
| 198 |
+
"SmthSmthV2": "DIR_N/A",
|
| 199 |
+
"HMDB51": "DIR_N/A",
|
| 200 |
+
"UCF101": "DIR_N/A",
|
| 201 |
+
"Breakfast": "DIR_N/A",
|
| 202 |
+
"MVBench": "DIR_N/A",
|
| 203 |
+
"Video-MME": "DIR_N/A",
|
| 204 |
+
"NExTQA": "DIR_N/A",
|
| 205 |
+
"EgoSchema": "DIR_N/A",
|
| 206 |
+
"ActivityNetQA": "DIR_N/A",
|
| 207 |
+
"DiDeMo": "DIR_N/A",
|
| 208 |
+
"MSR-VTT": "DIR_N/A",
|
| 209 |
+
"MSVD": "DIR_N/A",
|
| 210 |
+
"VATEX": "DIR_N/A",
|
| 211 |
+
"YouCook2": "DIR_N/A",
|
| 212 |
+
"QVHighlight": "DIR_N/A",
|
| 213 |
+
"Charades-STA": "DIR_N/A",
|
| 214 |
+
"MomentSeeker": "DIR_N/A"
|
| 215 |
+
},
|
| 216 |
+
"visdoc": {
|
| 217 |
+
"ViDoRe_arxivqa": "DIR_N/A",
|
| 218 |
+
"ViDoRe_docvqa": "DIR_N/A",
|
| 219 |
+
"ViDoRe_infovqa": "DIR_N/A",
|
| 220 |
+
"ViDoRe_tabfquad": "DIR_N/A",
|
| 221 |
+
"ViDoRe_tatdqa": "DIR_N/A",
|
| 222 |
+
"ViDoRe_shiftproject": "DIR_N/A",
|
| 223 |
+
"ViDoRe_syntheticDocQA_artificial_intelligence": "DIR_N/A",
|
| 224 |
+
"ViDoRe_syntheticDocQA_energy": "DIR_N/A",
|
| 225 |
+
"ViDoRe_syntheticDocQA_government_reports": "DIR_N/A",
|
| 226 |
+
"ViDoRe_syntheticDocQA_healthcare_industry": "DIR_N/A",
|
| 227 |
+
"ViDoRe_esg_reports_human_labeled_v2": "DIR_N/A",
|
| 228 |
+
"ViDoRe_biomedical_lectures_v2_multilingual": "DIR_N/A",
|
| 229 |
+
"ViDoRe_economics_reports_v2_multilingual": "DIR_N/A",
|
| 230 |
+
"ViDoRe_esg_reports_v2_multilingual": "DIR_N/A",
|
| 231 |
+
"VisRAG_ArxivQA": "DIR_N/A",
|
| 232 |
+
"VisRAG_ChartQA": "DIR_N/A",
|
| 233 |
+
"VisRAG_MP-DocVQA": "DIR_N/A",
|
| 234 |
+
"VisRAG_SlideVQA": "DIR_N/A",
|
| 235 |
+
"VisRAG_InfoVQA": "DIR_N/A",
|
| 236 |
+
"VisRAG_PlotQA": "DIR_N/A",
|
| 237 |
+
"ViDoSeek-page-fixed": "DIR_N/A",
|
| 238 |
+
"ViDoSeek-doc": "DIR_N/A",
|
| 239 |
+
"MMLongBench-page-fixed": "DIR_N/A",
|
| 240 |
+
"MMLongBench-doc": "DIR_N/A"
|
| 241 |
+
}
|
| 242 |
+
}
|
| 243 |
+
}
|
scores/ALICE-3B.json
ADDED
|
@@ -0,0 +1,243 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"model_name": "ALICE-3B",
|
| 4 |
+
"model_backbone": "Qwen2.5VL-3B",
|
| 5 |
+
"model_size": "3B parameters",
|
| 6 |
+
"embedding_dimension": null,
|
| 7 |
+
"max_length_tokens": null,
|
| 8 |
+
"model_release_date": "2026-5-11",
|
| 9 |
+
"data_source": "Self-Reported",
|
| 10 |
+
"url": null,
|
| 11 |
+
"report_generated_date": "2026-05-11T16:17:07.097653"
|
| 12 |
+
},
|
| 13 |
+
"metrics": {
|
| 14 |
+
"image": {
|
| 15 |
+
"ImageNet-1K": {
|
| 16 |
+
"acc": 0.828,
|
| 17 |
+
"num_correct": 828,
|
| 18 |
+
"num_pred": 1000
|
| 19 |
+
},
|
| 20 |
+
"N24News": {
|
| 21 |
+
"acc": 0.812,
|
| 22 |
+
"num_correct": 812,
|
| 23 |
+
"num_pred": 1000
|
| 24 |
+
},
|
| 25 |
+
"HatefulMemes": {
|
| 26 |
+
"acc": 0.759,
|
| 27 |
+
"num_correct": 759,
|
| 28 |
+
"num_pred": 1000
|
| 29 |
+
},
|
| 30 |
+
"VOC2007": {
|
| 31 |
+
"acc": 0.9,
|
| 32 |
+
"num_correct": 900,
|
| 33 |
+
"num_pred": 1000
|
| 34 |
+
},
|
| 35 |
+
"SUN397": {
|
| 36 |
+
"acc": 0.798,
|
| 37 |
+
"num_correct": 798,
|
| 38 |
+
"num_pred": 1000
|
| 39 |
+
},
|
| 40 |
+
"Place365": {
|
| 41 |
+
"acc": 0.463,
|
| 42 |
+
"num_correct": 463,
|
| 43 |
+
"num_pred": 1000
|
| 44 |
+
},
|
| 45 |
+
"ImageNet-A": {
|
| 46 |
+
"acc": 0.417,
|
| 47 |
+
"num_correct": 417,
|
| 48 |
+
"num_pred": 1000
|
| 49 |
+
},
|
| 50 |
+
"ImageNet-R": {
|
| 51 |
+
"acc": 0.822,
|
| 52 |
+
"num_correct": 822,
|
| 53 |
+
"num_pred": 1000
|
| 54 |
+
},
|
| 55 |
+
"ObjectNet": {
|
| 56 |
+
"acc": 0.626,
|
| 57 |
+
"num_correct": 626,
|
| 58 |
+
"num_pred": 1000
|
| 59 |
+
},
|
| 60 |
+
"Country211": {
|
| 61 |
+
"acc": 0.257,
|
| 62 |
+
"num_correct": 257,
|
| 63 |
+
"num_pred": 1000
|
| 64 |
+
},
|
| 65 |
+
"OK-VQA": {
|
| 66 |
+
"acc": 0.699,
|
| 67 |
+
"num_correct": 699,
|
| 68 |
+
"num_pred": 1000
|
| 69 |
+
},
|
| 70 |
+
"A-OKVQA": {
|
| 71 |
+
"acc": 0.61,
|
| 72 |
+
"num_correct": 610,
|
| 73 |
+
"num_pred": 1000
|
| 74 |
+
},
|
| 75 |
+
"DocVQA": {
|
| 76 |
+
"acc": 0.939,
|
| 77 |
+
"num_correct": 939,
|
| 78 |
+
"num_pred": 1000
|
| 79 |
+
},
|
| 80 |
+
"InfographicsVQA": {
|
| 81 |
+
"acc": 0.757,
|
| 82 |
+
"num_correct": 757,
|
| 83 |
+
"num_pred": 1000
|
| 84 |
+
},
|
| 85 |
+
"ChartQA": {
|
| 86 |
+
"acc": 0.698,
|
| 87 |
+
"num_correct": 698,
|
| 88 |
+
"num_pred": 1000
|
| 89 |
+
},
|
| 90 |
+
"Visual7W": {
|
| 91 |
+
"acc": 0.582,
|
| 92 |
+
"num_correct": 582,
|
| 93 |
+
"num_pred": 1000
|
| 94 |
+
},
|
| 95 |
+
"ScienceQA": {
|
| 96 |
+
"acc": 0.507,
|
| 97 |
+
"num_correct": 507,
|
| 98 |
+
"num_pred": 1000
|
| 99 |
+
},
|
| 100 |
+
"VizWiz": {
|
| 101 |
+
"acc": 0.502,
|
| 102 |
+
"num_correct": 502,
|
| 103 |
+
"num_pred": 1000
|
| 104 |
+
},
|
| 105 |
+
"GQA": {
|
| 106 |
+
"acc": 0.758,
|
| 107 |
+
"num_correct": 758,
|
| 108 |
+
"num_pred": 1000
|
| 109 |
+
},
|
| 110 |
+
"TextVQA": {
|
| 111 |
+
"acc": 0.819,
|
| 112 |
+
"num_correct": 819,
|
| 113 |
+
"num_pred": 1000
|
| 114 |
+
},
|
| 115 |
+
"VisDial": {
|
| 116 |
+
"acc": 0.845,
|
| 117 |
+
"num_correct": 845,
|
| 118 |
+
"num_pred": 1000
|
| 119 |
+
},
|
| 120 |
+
"CIRR": {
|
| 121 |
+
"acc": 0.58,
|
| 122 |
+
"num_correct": 580,
|
| 123 |
+
"num_pred": 1000
|
| 124 |
+
},
|
| 125 |
+
"VisualNews_t2i": {
|
| 126 |
+
"acc": 0.767,
|
| 127 |
+
"num_correct": 767,
|
| 128 |
+
"num_pred": 1000
|
| 129 |
+
},
|
| 130 |
+
"VisualNews_i2t": {
|
| 131 |
+
"acc": 0.816,
|
| 132 |
+
"num_correct": 816,
|
| 133 |
+
"num_pred": 1000
|
| 134 |
+
},
|
| 135 |
+
"MSCOCO_t2i": {
|
| 136 |
+
"acc": 0.791,
|
| 137 |
+
"num_correct": 791,
|
| 138 |
+
"num_pred": 1000
|
| 139 |
+
},
|
| 140 |
+
"MSCOCO_i2t": {
|
| 141 |
+
"acc": 0.756,
|
| 142 |
+
"num_correct": 756,
|
| 143 |
+
"num_pred": 1000
|
| 144 |
+
},
|
| 145 |
+
"NIGHTS": {
|
| 146 |
+
"acc": 0.678,
|
| 147 |
+
"num_correct": 678,
|
| 148 |
+
"num_pred": 1000
|
| 149 |
+
},
|
| 150 |
+
"WebQA": {
|
| 151 |
+
"acc": 0.905,
|
| 152 |
+
"num_correct": 905,
|
| 153 |
+
"num_pred": 1000
|
| 154 |
+
},
|
| 155 |
+
"FashionIQ": {
|
| 156 |
+
"acc": 0.249,
|
| 157 |
+
"num_correct": 249,
|
| 158 |
+
"num_pred": 1000
|
| 159 |
+
},
|
| 160 |
+
"Wiki-SS-NQ": {
|
| 161 |
+
"acc": 0.673,
|
| 162 |
+
"num_correct": 673,
|
| 163 |
+
"num_pred": 1000
|
| 164 |
+
},
|
| 165 |
+
"OVEN": {
|
| 166 |
+
"acc": 0.704,
|
| 167 |
+
"num_correct": 704,
|
| 168 |
+
"num_pred": 1000
|
| 169 |
+
},
|
| 170 |
+
"EDIS": {
|
| 171 |
+
"acc": 0.927,
|
| 172 |
+
"num_correct": 927,
|
| 173 |
+
"num_pred": 1000
|
| 174 |
+
},
|
| 175 |
+
"MSCOCO": {
|
| 176 |
+
"acc": 0.878,
|
| 177 |
+
"num_correct": 878,
|
| 178 |
+
"num_pred": 1000
|
| 179 |
+
},
|
| 180 |
+
"RefCOCO": {
|
| 181 |
+
"acc": 0.942,
|
| 182 |
+
"num_correct": 942,
|
| 183 |
+
"num_pred": 1000
|
| 184 |
+
},
|
| 185 |
+
"RefCOCO-Matching": {
|
| 186 |
+
"acc": 0.936,
|
| 187 |
+
"num_correct": 936,
|
| 188 |
+
"num_pred": 1000
|
| 189 |
+
},
|
| 190 |
+
"Visual7W-Pointing": {
|
| 191 |
+
"acc": 0.866,
|
| 192 |
+
"num_correct": 866,
|
| 193 |
+
"num_pred": 1000
|
| 194 |
+
}
|
| 195 |
+
},
|
| 196 |
+
"video": {
|
| 197 |
+
"K700": "DIR_N/A",
|
| 198 |
+
"SmthSmthV2": "DIR_N/A",
|
| 199 |
+
"HMDB51": "DIR_N/A",
|
| 200 |
+
"UCF101": "DIR_N/A",
|
| 201 |
+
"Breakfast": "DIR_N/A",
|
| 202 |
+
"MVBench": "DIR_N/A",
|
| 203 |
+
"Video-MME": "DIR_N/A",
|
| 204 |
+
"NExTQA": "DIR_N/A",
|
| 205 |
+
"EgoSchema": "DIR_N/A",
|
| 206 |
+
"ActivityNetQA": "DIR_N/A",
|
| 207 |
+
"DiDeMo": "DIR_N/A",
|
| 208 |
+
"MSR-VTT": "DIR_N/A",
|
| 209 |
+
"MSVD": "DIR_N/A",
|
| 210 |
+
"VATEX": "DIR_N/A",
|
| 211 |
+
"YouCook2": "DIR_N/A",
|
| 212 |
+
"QVHighlight": "DIR_N/A",
|
| 213 |
+
"Charades-STA": "DIR_N/A",
|
| 214 |
+
"MomentSeeker": "DIR_N/A"
|
| 215 |
+
},
|
| 216 |
+
"visdoc": {
|
| 217 |
+
"ViDoRe_arxivqa": "DIR_N/A",
|
| 218 |
+
"ViDoRe_docvqa": "DIR_N/A",
|
| 219 |
+
"ViDoRe_infovqa": "DIR_N/A",
|
| 220 |
+
"ViDoRe_tabfquad": "DIR_N/A",
|
| 221 |
+
"ViDoRe_tatdqa": "DIR_N/A",
|
| 222 |
+
"ViDoRe_shiftproject": "DIR_N/A",
|
| 223 |
+
"ViDoRe_syntheticDocQA_artificial_intelligence": "DIR_N/A",
|
| 224 |
+
"ViDoRe_syntheticDocQA_energy": "DIR_N/A",
|
| 225 |
+
"ViDoRe_syntheticDocQA_government_reports": "DIR_N/A",
|
| 226 |
+
"ViDoRe_syntheticDocQA_healthcare_industry": "DIR_N/A",
|
| 227 |
+
"ViDoRe_esg_reports_human_labeled_v2": "DIR_N/A",
|
| 228 |
+
"ViDoRe_biomedical_lectures_v2_multilingual": "DIR_N/A",
|
| 229 |
+
"ViDoRe_economics_reports_v2_multilingual": "DIR_N/A",
|
| 230 |
+
"ViDoRe_esg_reports_v2_multilingual": "DIR_N/A",
|
| 231 |
+
"VisRAG_ArxivQA": "DIR_N/A",
|
| 232 |
+
"VisRAG_ChartQA": "DIR_N/A",
|
| 233 |
+
"VisRAG_MP-DocVQA": "DIR_N/A",
|
| 234 |
+
"VisRAG_SlideVQA": "DIR_N/A",
|
| 235 |
+
"VisRAG_InfoVQA": "DIR_N/A",
|
| 236 |
+
"VisRAG_PlotQA": "DIR_N/A",
|
| 237 |
+
"ViDoSeek-page-fixed": "DIR_N/A",
|
| 238 |
+
"ViDoSeek-doc": "DIR_N/A",
|
| 239 |
+
"MMLongBench-page-fixed": "DIR_N/A",
|
| 240 |
+
"MMLongBench-doc": "DIR_N/A"
|
| 241 |
+
}
|
| 242 |
+
}
|
| 243 |
+
}
|
scores/ALICE-4B.json
ADDED
|
@@ -0,0 +1,243 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"model_name": "ALICE-4B",
|
| 4 |
+
"model_backbone": "Qwen3VL-4B",
|
| 5 |
+
"model_size": "4B parameters",
|
| 6 |
+
"embedding_dimension": null,
|
| 7 |
+
"max_length_tokens": null,
|
| 8 |
+
"model_release_date": "2026-5-11",
|
| 9 |
+
"data_source": "Self-Reported",
|
| 10 |
+
"url": null,
|
| 11 |
+
"report_generated_date": "2026-05-11T16:17:05.956770"
|
| 12 |
+
},
|
| 13 |
+
"metrics": {
|
| 14 |
+
"image": {
|
| 15 |
+
"ImageNet-1K": {
|
| 16 |
+
"acc": 0.848,
|
| 17 |
+
"num_correct": 848,
|
| 18 |
+
"num_pred": 1000
|
| 19 |
+
},
|
| 20 |
+
"N24News": {
|
| 21 |
+
"acc": 0.804,
|
| 22 |
+
"num_correct": 804,
|
| 23 |
+
"num_pred": 1000
|
| 24 |
+
},
|
| 25 |
+
"HatefulMemes": {
|
| 26 |
+
"acc": 0.742,
|
| 27 |
+
"num_correct": 742,
|
| 28 |
+
"num_pred": 1000
|
| 29 |
+
},
|
| 30 |
+
"VOC2007": {
|
| 31 |
+
"acc": 0.923,
|
| 32 |
+
"num_correct": 923,
|
| 33 |
+
"num_pred": 1000
|
| 34 |
+
},
|
| 35 |
+
"SUN397": {
|
| 36 |
+
"acc": 0.828,
|
| 37 |
+
"num_correct": 828,
|
| 38 |
+
"num_pred": 1000
|
| 39 |
+
},
|
| 40 |
+
"Place365": {
|
| 41 |
+
"acc": 0.46,
|
| 42 |
+
"num_correct": 460,
|
| 43 |
+
"num_pred": 1000
|
| 44 |
+
},
|
| 45 |
+
"ImageNet-A": {
|
| 46 |
+
"acc": 0.515,
|
| 47 |
+
"num_correct": 515,
|
| 48 |
+
"num_pred": 1000
|
| 49 |
+
},
|
| 50 |
+
"ImageNet-R": {
|
| 51 |
+
"acc": 0.903,
|
| 52 |
+
"num_correct": 903,
|
| 53 |
+
"num_pred": 1000
|
| 54 |
+
},
|
| 55 |
+
"ObjectNet": {
|
| 56 |
+
"acc": 0.744,
|
| 57 |
+
"num_correct": 744,
|
| 58 |
+
"num_pred": 1000
|
| 59 |
+
},
|
| 60 |
+
"Country211": {
|
| 61 |
+
"acc": 0.178,
|
| 62 |
+
"num_correct": 178,
|
| 63 |
+
"num_pred": 1000
|
| 64 |
+
},
|
| 65 |
+
"OK-VQA": {
|
| 66 |
+
"acc": 0.708,
|
| 67 |
+
"num_correct": 708,
|
| 68 |
+
"num_pred": 1000
|
| 69 |
+
},
|
| 70 |
+
"A-OKVQA": {
|
| 71 |
+
"acc": 0.607,
|
| 72 |
+
"num_correct": 607,
|
| 73 |
+
"num_pred": 1000
|
| 74 |
+
},
|
| 75 |
+
"DocVQA": {
|
| 76 |
+
"acc": 0.943,
|
| 77 |
+
"num_correct": 943,
|
| 78 |
+
"num_pred": 1000
|
| 79 |
+
},
|
| 80 |
+
"InfographicsVQA": {
|
| 81 |
+
"acc": 0.72,
|
| 82 |
+
"num_correct": 720,
|
| 83 |
+
"num_pred": 1000
|
| 84 |
+
},
|
| 85 |
+
"ChartQA": {
|
| 86 |
+
"acc": 0.682,
|
| 87 |
+
"num_correct": 682,
|
| 88 |
+
"num_pred": 1000
|
| 89 |
+
},
|
| 90 |
+
"Visual7W": {
|
| 91 |
+
"acc": 0.582,
|
| 92 |
+
"num_correct": 582,
|
| 93 |
+
"num_pred": 1000
|
| 94 |
+
},
|
| 95 |
+
"ScienceQA": {
|
| 96 |
+
"acc": 0.545,
|
| 97 |
+
"num_correct": 545,
|
| 98 |
+
"num_pred": 1000
|
| 99 |
+
},
|
| 100 |
+
"VizWiz": {
|
| 101 |
+
"acc": 0.489,
|
| 102 |
+
"num_correct": 489,
|
| 103 |
+
"num_pred": 1000
|
| 104 |
+
},
|
| 105 |
+
"GQA": {
|
| 106 |
+
"acc": 0.756,
|
| 107 |
+
"num_correct": 756,
|
| 108 |
+
"num_pred": 1000
|
| 109 |
+
},
|
| 110 |
+
"TextVQA": {
|
| 111 |
+
"acc": 0.828,
|
| 112 |
+
"num_correct": 828,
|
| 113 |
+
"num_pred": 1000
|
| 114 |
+
},
|
| 115 |
+
"VisDial": {
|
| 116 |
+
"acc": 0.886,
|
| 117 |
+
"num_correct": 886,
|
| 118 |
+
"num_pred": 1000
|
| 119 |
+
},
|
| 120 |
+
"CIRR": {
|
| 121 |
+
"acc": 0.626,
|
| 122 |
+
"num_correct": 626,
|
| 123 |
+
"num_pred": 1000
|
| 124 |
+
},
|
| 125 |
+
"VisualNews_t2i": {
|
| 126 |
+
"acc": 0.754,
|
| 127 |
+
"num_correct": 754,
|
| 128 |
+
"num_pred": 1000
|
| 129 |
+
},
|
| 130 |
+
"VisualNews_i2t": {
|
| 131 |
+
"acc": 0.816,
|
| 132 |
+
"num_correct": 816,
|
| 133 |
+
"num_pred": 1000
|
| 134 |
+
},
|
| 135 |
+
"MSCOCO_t2i": {
|
| 136 |
+
"acc": 0.828,
|
| 137 |
+
"num_correct": 828,
|
| 138 |
+
"num_pred": 1000
|
| 139 |
+
},
|
| 140 |
+
"MSCOCO_i2t": {
|
| 141 |
+
"acc": 0.784,
|
| 142 |
+
"num_correct": 784,
|
| 143 |
+
"num_pred": 1000
|
| 144 |
+
},
|
| 145 |
+
"NIGHTS": {
|
| 146 |
+
"acc": 0.681,
|
| 147 |
+
"num_correct": 681,
|
| 148 |
+
"num_pred": 1000
|
| 149 |
+
},
|
| 150 |
+
"WebQA": {
|
| 151 |
+
"acc": 0.905,
|
| 152 |
+
"num_correct": 905,
|
| 153 |
+
"num_pred": 1000
|
| 154 |
+
},
|
| 155 |
+
"FashionIQ": {
|
| 156 |
+
"acc": 0.313,
|
| 157 |
+
"num_correct": 313,
|
| 158 |
+
"num_pred": 1000
|
| 159 |
+
},
|
| 160 |
+
"Wiki-SS-NQ": {
|
| 161 |
+
"acc": 0.65,
|
| 162 |
+
"num_correct": 650,
|
| 163 |
+
"num_pred": 1000
|
| 164 |
+
},
|
| 165 |
+
"OVEN": {
|
| 166 |
+
"acc": 0.65,
|
| 167 |
+
"num_correct": 650,
|
| 168 |
+
"num_pred": 1000
|
| 169 |
+
},
|
| 170 |
+
"EDIS": {
|
| 171 |
+
"acc": 0.892,
|
| 172 |
+
"num_correct": 892,
|
| 173 |
+
"num_pred": 1000
|
| 174 |
+
},
|
| 175 |
+
"MSCOCO": {
|
| 176 |
+
"acc": 0.912,
|
| 177 |
+
"num_correct": 912,
|
| 178 |
+
"num_pred": 1000
|
| 179 |
+
},
|
| 180 |
+
"RefCOCO": {
|
| 181 |
+
"acc": 0.951,
|
| 182 |
+
"num_correct": 951,
|
| 183 |
+
"num_pred": 1000
|
| 184 |
+
},
|
| 185 |
+
"RefCOCO-Matching": {
|
| 186 |
+
"acc": 0.933,
|
| 187 |
+
"num_correct": 933,
|
| 188 |
+
"num_pred": 1000
|
| 189 |
+
},
|
| 190 |
+
"Visual7W-Pointing": {
|
| 191 |
+
"acc": 0.834,
|
| 192 |
+
"num_correct": 834,
|
| 193 |
+
"num_pred": 1000
|
| 194 |
+
}
|
| 195 |
+
},
|
| 196 |
+
"video": {
|
| 197 |
+
"K700": "DIR_N/A",
|
| 198 |
+
"SmthSmthV2": "DIR_N/A",
|
| 199 |
+
"HMDB51": "DIR_N/A",
|
| 200 |
+
"UCF101": "DIR_N/A",
|
| 201 |
+
"Breakfast": "DIR_N/A",
|
| 202 |
+
"MVBench": "DIR_N/A",
|
| 203 |
+
"Video-MME": "DIR_N/A",
|
| 204 |
+
"NExTQA": "DIR_N/A",
|
| 205 |
+
"EgoSchema": "DIR_N/A",
|
| 206 |
+
"ActivityNetQA": "DIR_N/A",
|
| 207 |
+
"DiDeMo": "DIR_N/A",
|
| 208 |
+
"MSR-VTT": "DIR_N/A",
|
| 209 |
+
"MSVD": "DIR_N/A",
|
| 210 |
+
"VATEX": "DIR_N/A",
|
| 211 |
+
"YouCook2": "DIR_N/A",
|
| 212 |
+
"QVHighlight": "DIR_N/A",
|
| 213 |
+
"Charades-STA": "DIR_N/A",
|
| 214 |
+
"MomentSeeker": "DIR_N/A"
|
| 215 |
+
},
|
| 216 |
+
"visdoc": {
|
| 217 |
+
"ViDoRe_arxivqa": "DIR_N/A",
|
| 218 |
+
"ViDoRe_docvqa": "DIR_N/A",
|
| 219 |
+
"ViDoRe_infovqa": "DIR_N/A",
|
| 220 |
+
"ViDoRe_tabfquad": "DIR_N/A",
|
| 221 |
+
"ViDoRe_tatdqa": "DIR_N/A",
|
| 222 |
+
"ViDoRe_shiftproject": "DIR_N/A",
|
| 223 |
+
"ViDoRe_syntheticDocQA_artificial_intelligence": "DIR_N/A",
|
| 224 |
+
"ViDoRe_syntheticDocQA_energy": "DIR_N/A",
|
| 225 |
+
"ViDoRe_syntheticDocQA_government_reports": "DIR_N/A",
|
| 226 |
+
"ViDoRe_syntheticDocQA_healthcare_industry": "DIR_N/A",
|
| 227 |
+
"ViDoRe_esg_reports_human_labeled_v2": "DIR_N/A",
|
| 228 |
+
"ViDoRe_biomedical_lectures_v2_multilingual": "DIR_N/A",
|
| 229 |
+
"ViDoRe_economics_reports_v2_multilingual": "DIR_N/A",
|
| 230 |
+
"ViDoRe_esg_reports_v2_multilingual": "DIR_N/A",
|
| 231 |
+
"VisRAG_ArxivQA": "DIR_N/A",
|
| 232 |
+
"VisRAG_ChartQA": "DIR_N/A",
|
| 233 |
+
"VisRAG_MP-DocVQA": "DIR_N/A",
|
| 234 |
+
"VisRAG_SlideVQA": "DIR_N/A",
|
| 235 |
+
"VisRAG_InfoVQA": "DIR_N/A",
|
| 236 |
+
"VisRAG_PlotQA": "DIR_N/A",
|
| 237 |
+
"ViDoSeek-page-fixed": "DIR_N/A",
|
| 238 |
+
"ViDoSeek-doc": "DIR_N/A",
|
| 239 |
+
"MMLongBench-page-fixed": "DIR_N/A",
|
| 240 |
+
"MMLongBench-doc": "DIR_N/A"
|
| 241 |
+
}
|
| 242 |
+
}
|
| 243 |
+
}
|
scores/ALICE-7B.json
ADDED
|
@@ -0,0 +1,243 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"model_name": "ALICE-7B",
|
| 4 |
+
"model_backbone": "Qwen2.5VL-7B",
|
| 5 |
+
"model_size": "7B parameters",
|
| 6 |
+
"embedding_dimension": null,
|
| 7 |
+
"max_length_tokens": null,
|
| 8 |
+
"model_release_date": "2026-5-11",
|
| 9 |
+
"data_source": "Self-Reported",
|
| 10 |
+
"url": null,
|
| 11 |
+
"report_generated_date": "2026-05-11T16:17:06.292871"
|
| 12 |
+
},
|
| 13 |
+
"metrics": {
|
| 14 |
+
"image": {
|
| 15 |
+
"ImageNet-1K": {
|
| 16 |
+
"acc": 0.834,
|
| 17 |
+
"num_correct": 834,
|
| 18 |
+
"num_pred": 1000
|
| 19 |
+
},
|
| 20 |
+
"N24News": {
|
| 21 |
+
"acc": 0.823,
|
| 22 |
+
"num_correct": 823,
|
| 23 |
+
"num_pred": 1000
|
| 24 |
+
},
|
| 25 |
+
"HatefulMemes": {
|
| 26 |
+
"acc": 0.798,
|
| 27 |
+
"num_correct": 798,
|
| 28 |
+
"num_pred": 1000
|
| 29 |
+
},
|
| 30 |
+
"VOC2007": {
|
| 31 |
+
"acc": 0.898,
|
| 32 |
+
"num_correct": 898,
|
| 33 |
+
"num_pred": 1000
|
| 34 |
+
},
|
| 35 |
+
"SUN397": {
|
| 36 |
+
"acc": 0.823,
|
| 37 |
+
"num_correct": 823,
|
| 38 |
+
"num_pred": 1000
|
| 39 |
+
},
|
| 40 |
+
"Place365": {
|
| 41 |
+
"acc": 0.448,
|
| 42 |
+
"num_correct": 448,
|
| 43 |
+
"num_pred": 1000
|
| 44 |
+
},
|
| 45 |
+
"ImageNet-A": {
|
| 46 |
+
"acc": 0.48,
|
| 47 |
+
"num_correct": 480,
|
| 48 |
+
"num_pred": 1000
|
| 49 |
+
},
|
| 50 |
+
"ImageNet-R": {
|
| 51 |
+
"acc": 0.806,
|
| 52 |
+
"num_correct": 806,
|
| 53 |
+
"num_pred": 1000
|
| 54 |
+
},
|
| 55 |
+
"ObjectNet": {
|
| 56 |
+
"acc": 0.655,
|
| 57 |
+
"num_correct": 655,
|
| 58 |
+
"num_pred": 1000
|
| 59 |
+
},
|
| 60 |
+
"Country211": {
|
| 61 |
+
"acc": 0.284,
|
| 62 |
+
"num_correct": 284,
|
| 63 |
+
"num_pred": 1000
|
| 64 |
+
},
|
| 65 |
+
"OK-VQA": {
|
| 66 |
+
"acc": 0.741,
|
| 67 |
+
"num_correct": 741,
|
| 68 |
+
"num_pred": 1000
|
| 69 |
+
},
|
| 70 |
+
"A-OKVQA": {
|
| 71 |
+
"acc": 0.642,
|
| 72 |
+
"num_correct": 642,
|
| 73 |
+
"num_pred": 1000
|
| 74 |
+
},
|
| 75 |
+
"DocVQA": {
|
| 76 |
+
"acc": 0.945,
|
| 77 |
+
"num_correct": 945,
|
| 78 |
+
"num_pred": 1000
|
| 79 |
+
},
|
| 80 |
+
"InfographicsVQA": {
|
| 81 |
+
"acc": 0.781,
|
| 82 |
+
"num_correct": 781,
|
| 83 |
+
"num_pred": 1000
|
| 84 |
+
},
|
| 85 |
+
"ChartQA": {
|
| 86 |
+
"acc": 0.753,
|
| 87 |
+
"num_correct": 753,
|
| 88 |
+
"num_pred": 1000
|
| 89 |
+
},
|
| 90 |
+
"Visual7W": {
|
| 91 |
+
"acc": 0.594,
|
| 92 |
+
"num_correct": 594,
|
| 93 |
+
"num_pred": 1000
|
| 94 |
+
},
|
| 95 |
+
"ScienceQA": {
|
| 96 |
+
"acc": 0.54,
|
| 97 |
+
"num_correct": 540,
|
| 98 |
+
"num_pred": 1000
|
| 99 |
+
},
|
| 100 |
+
"VizWiz": {
|
| 101 |
+
"acc": 0.514,
|
| 102 |
+
"num_correct": 514,
|
| 103 |
+
"num_pred": 1000
|
| 104 |
+
},
|
| 105 |
+
"GQA": {
|
| 106 |
+
"acc": 0.779,
|
| 107 |
+
"num_correct": 779,
|
| 108 |
+
"num_pred": 1000
|
| 109 |
+
},
|
| 110 |
+
"TextVQA": {
|
| 111 |
+
"acc": 0.83,
|
| 112 |
+
"num_correct": 830,
|
| 113 |
+
"num_pred": 1000
|
| 114 |
+
},
|
| 115 |
+
"VisDial": {
|
| 116 |
+
"acc": 0.866,
|
| 117 |
+
"num_correct": 866,
|
| 118 |
+
"num_pred": 1000
|
| 119 |
+
},
|
| 120 |
+
"CIRR": {
|
| 121 |
+
"acc": 0.617,
|
| 122 |
+
"num_correct": 617,
|
| 123 |
+
"num_pred": 1000
|
| 124 |
+
},
|
| 125 |
+
"VisualNews_t2i": {
|
| 126 |
+
"acc": 0.798,
|
| 127 |
+
"num_correct": 798,
|
| 128 |
+
"num_pred": 1000
|
| 129 |
+
},
|
| 130 |
+
"VisualNews_i2t": {
|
| 131 |
+
"acc": 0.822,
|
| 132 |
+
"num_correct": 822,
|
| 133 |
+
"num_pred": 1000
|
| 134 |
+
},
|
| 135 |
+
"MSCOCO_t2i": {
|
| 136 |
+
"acc": 0.795,
|
| 137 |
+
"num_correct": 795,
|
| 138 |
+
"num_pred": 1000
|
| 139 |
+
},
|
| 140 |
+
"MSCOCO_i2t": {
|
| 141 |
+
"acc": 0.77,
|
| 142 |
+
"num_correct": 770,
|
| 143 |
+
"num_pred": 1000
|
| 144 |
+
},
|
| 145 |
+
"NIGHTS": {
|
| 146 |
+
"acc": 0.679,
|
| 147 |
+
"num_correct": 679,
|
| 148 |
+
"num_pred": 1000
|
| 149 |
+
},
|
| 150 |
+
"WebQA": {
|
| 151 |
+
"acc": 0.906,
|
| 152 |
+
"num_correct": 906,
|
| 153 |
+
"num_pred": 1000
|
| 154 |
+
},
|
| 155 |
+
"FashionIQ": {
|
| 156 |
+
"acc": 0.275,
|
| 157 |
+
"num_correct": 275,
|
| 158 |
+
"num_pred": 1000
|
| 159 |
+
},
|
| 160 |
+
"Wiki-SS-NQ": {
|
| 161 |
+
"acc": 0.648,
|
| 162 |
+
"num_correct": 648,
|
| 163 |
+
"num_pred": 1000
|
| 164 |
+
},
|
| 165 |
+
"OVEN": {
|
| 166 |
+
"acc": 0.739,
|
| 167 |
+
"num_correct": 739,
|
| 168 |
+
"num_pred": 1000
|
| 169 |
+
},
|
| 170 |
+
"EDIS": {
|
| 171 |
+
"acc": 0.928,
|
| 172 |
+
"num_correct": 928,
|
| 173 |
+
"num_pred": 1000
|
| 174 |
+
},
|
| 175 |
+
"MSCOCO": {
|
| 176 |
+
"acc": 0.884,
|
| 177 |
+
"num_correct": 884,
|
| 178 |
+
"num_pred": 1000
|
| 179 |
+
},
|
| 180 |
+
"RefCOCO": {
|
| 181 |
+
"acc": 0.953,
|
| 182 |
+
"num_correct": 953,
|
| 183 |
+
"num_pred": 1000
|
| 184 |
+
},
|
| 185 |
+
"RefCOCO-Matching": {
|
| 186 |
+
"acc": 0.936,
|
| 187 |
+
"num_correct": 936,
|
| 188 |
+
"num_pred": 1000
|
| 189 |
+
},
|
| 190 |
+
"Visual7W-Pointing": {
|
| 191 |
+
"acc": 0.844,
|
| 192 |
+
"num_correct": 844,
|
| 193 |
+
"num_pred": 1000
|
| 194 |
+
}
|
| 195 |
+
},
|
| 196 |
+
"video": {
|
| 197 |
+
"K700": "DIR_N/A",
|
| 198 |
+
"SmthSmthV2": "DIR_N/A",
|
| 199 |
+
"HMDB51": "DIR_N/A",
|
| 200 |
+
"UCF101": "DIR_N/A",
|
| 201 |
+
"Breakfast": "DIR_N/A",
|
| 202 |
+
"MVBench": "DIR_N/A",
|
| 203 |
+
"Video-MME": "DIR_N/A",
|
| 204 |
+
"NExTQA": "DIR_N/A",
|
| 205 |
+
"EgoSchema": "DIR_N/A",
|
| 206 |
+
"ActivityNetQA": "DIR_N/A",
|
| 207 |
+
"DiDeMo": "DIR_N/A",
|
| 208 |
+
"MSR-VTT": "DIR_N/A",
|
| 209 |
+
"MSVD": "DIR_N/A",
|
| 210 |
+
"VATEX": "DIR_N/A",
|
| 211 |
+
"YouCook2": "DIR_N/A",
|
| 212 |
+
"QVHighlight": "DIR_N/A",
|
| 213 |
+
"Charades-STA": "DIR_N/A",
|
| 214 |
+
"MomentSeeker": "DIR_N/A"
|
| 215 |
+
},
|
| 216 |
+
"visdoc": {
|
| 217 |
+
"ViDoRe_arxivqa": "DIR_N/A",
|
| 218 |
+
"ViDoRe_docvqa": "DIR_N/A",
|
| 219 |
+
"ViDoRe_infovqa": "DIR_N/A",
|
| 220 |
+
"ViDoRe_tabfquad": "DIR_N/A",
|
| 221 |
+
"ViDoRe_tatdqa": "DIR_N/A",
|
| 222 |
+
"ViDoRe_shiftproject": "DIR_N/A",
|
| 223 |
+
"ViDoRe_syntheticDocQA_artificial_intelligence": "DIR_N/A",
|
| 224 |
+
"ViDoRe_syntheticDocQA_energy": "DIR_N/A",
|
| 225 |
+
"ViDoRe_syntheticDocQA_government_reports": "DIR_N/A",
|
| 226 |
+
"ViDoRe_syntheticDocQA_healthcare_industry": "DIR_N/A",
|
| 227 |
+
"ViDoRe_esg_reports_human_labeled_v2": "DIR_N/A",
|
| 228 |
+
"ViDoRe_biomedical_lectures_v2_multilingual": "DIR_N/A",
|
| 229 |
+
"ViDoRe_economics_reports_v2_multilingual": "DIR_N/A",
|
| 230 |
+
"ViDoRe_esg_reports_v2_multilingual": "DIR_N/A",
|
| 231 |
+
"VisRAG_ArxivQA": "DIR_N/A",
|
| 232 |
+
"VisRAG_ChartQA": "DIR_N/A",
|
| 233 |
+
"VisRAG_MP-DocVQA": "DIR_N/A",
|
| 234 |
+
"VisRAG_SlideVQA": "DIR_N/A",
|
| 235 |
+
"VisRAG_InfoVQA": "DIR_N/A",
|
| 236 |
+
"VisRAG_PlotQA": "DIR_N/A",
|
| 237 |
+
"ViDoSeek-page-fixed": "DIR_N/A",
|
| 238 |
+
"ViDoSeek-doc": "DIR_N/A",
|
| 239 |
+
"MMLongBench-page-fixed": "DIR_N/A",
|
| 240 |
+
"MMLongBench-doc": "DIR_N/A"
|
| 241 |
+
}
|
| 242 |
+
}
|
| 243 |
+
}
|
scores/ALICE-8B.json
ADDED
|
@@ -0,0 +1,243 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"model_name": "ALICE-8B",
|
| 4 |
+
"model_backbone": "Qwen3VL-8B",
|
| 5 |
+
"model_size": "8B parameters",
|
| 6 |
+
"embedding_dimension": null,
|
| 7 |
+
"max_length_tokens": null,
|
| 8 |
+
"model_release_date": "2026-5-11",
|
| 9 |
+
"data_source": "Self-Reported",
|
| 10 |
+
"url": null,
|
| 11 |
+
"report_generated_date": "2026-05-11T16:17:07.468738"
|
| 12 |
+
},
|
| 13 |
+
"metrics": {
|
| 14 |
+
"image": {
|
| 15 |
+
"ImageNet-1K": {
|
| 16 |
+
"acc": 0.831,
|
| 17 |
+
"num_correct": 831,
|
| 18 |
+
"num_pred": 1000
|
| 19 |
+
},
|
| 20 |
+
"N24News": {
|
| 21 |
+
"acc": 0.822,
|
| 22 |
+
"num_correct": 822,
|
| 23 |
+
"num_pred": 1000
|
| 24 |
+
},
|
| 25 |
+
"HatefulMemes": {
|
| 26 |
+
"acc": 0.785,
|
| 27 |
+
"num_correct": 785,
|
| 28 |
+
"num_pred": 1000
|
| 29 |
+
},
|
| 30 |
+
"VOC2007": {
|
| 31 |
+
"acc": 0.93,
|
| 32 |
+
"num_correct": 930,
|
| 33 |
+
"num_pred": 1000
|
| 34 |
+
},
|
| 35 |
+
"SUN397": {
|
| 36 |
+
"acc": 0.826,
|
| 37 |
+
"num_correct": 826,
|
| 38 |
+
"num_pred": 1000
|
| 39 |
+
},
|
| 40 |
+
"Place365": {
|
| 41 |
+
"acc": 0.479,
|
| 42 |
+
"num_correct": 479,
|
| 43 |
+
"num_pred": 1000
|
| 44 |
+
},
|
| 45 |
+
"ImageNet-A": {
|
| 46 |
+
"acc": 0.538,
|
| 47 |
+
"num_correct": 538,
|
| 48 |
+
"num_pred": 1000
|
| 49 |
+
},
|
| 50 |
+
"ImageNet-R": {
|
| 51 |
+
"acc": 0.877,
|
| 52 |
+
"num_correct": 877,
|
| 53 |
+
"num_pred": 1000
|
| 54 |
+
},
|
| 55 |
+
"ObjectNet": {
|
| 56 |
+
"acc": 0.743,
|
| 57 |
+
"num_correct": 743,
|
| 58 |
+
"num_pred": 1000
|
| 59 |
+
},
|
| 60 |
+
"Country211": {
|
| 61 |
+
"acc": 0.208,
|
| 62 |
+
"num_correct": 208,
|
| 63 |
+
"num_pred": 1000
|
| 64 |
+
},
|
| 65 |
+
"OK-VQA": {
|
| 66 |
+
"acc": 0.735,
|
| 67 |
+
"num_correct": 735,
|
| 68 |
+
"num_pred": 1000
|
| 69 |
+
},
|
| 70 |
+
"A-OKVQA": {
|
| 71 |
+
"acc": 0.65,
|
| 72 |
+
"num_correct": 650,
|
| 73 |
+
"num_pred": 1000
|
| 74 |
+
},
|
| 75 |
+
"DocVQA": {
|
| 76 |
+
"acc": 0.942,
|
| 77 |
+
"num_correct": 942,
|
| 78 |
+
"num_pred": 1000
|
| 79 |
+
},
|
| 80 |
+
"InfographicsVQA": {
|
| 81 |
+
"acc": 0.754,
|
| 82 |
+
"num_correct": 754,
|
| 83 |
+
"num_pred": 1000
|
| 84 |
+
},
|
| 85 |
+
"ChartQA": {
|
| 86 |
+
"acc": 0.728,
|
| 87 |
+
"num_correct": 728,
|
| 88 |
+
"num_pred": 1000
|
| 89 |
+
},
|
| 90 |
+
"Visual7W": {
|
| 91 |
+
"acc": 0.593,
|
| 92 |
+
"num_correct": 593,
|
| 93 |
+
"num_pred": 1000
|
| 94 |
+
},
|
| 95 |
+
"ScienceQA": {
|
| 96 |
+
"acc": 0.551,
|
| 97 |
+
"num_correct": 551,
|
| 98 |
+
"num_pred": 1000
|
| 99 |
+
},
|
| 100 |
+
"VizWiz": {
|
| 101 |
+
"acc": 0.51,
|
| 102 |
+
"num_correct": 510,
|
| 103 |
+
"num_pred": 1000
|
| 104 |
+
},
|
| 105 |
+
"GQA": {
|
| 106 |
+
"acc": 0.742,
|
| 107 |
+
"num_correct": 742,
|
| 108 |
+
"num_pred": 1000
|
| 109 |
+
},
|
| 110 |
+
"TextVQA": {
|
| 111 |
+
"acc": 0.848,
|
| 112 |
+
"num_correct": 848,
|
| 113 |
+
"num_pred": 1000
|
| 114 |
+
},
|
| 115 |
+
"VisDial": {
|
| 116 |
+
"acc": 0.875,
|
| 117 |
+
"num_correct": 875,
|
| 118 |
+
"num_pred": 1000
|
| 119 |
+
},
|
| 120 |
+
"CIRR": {
|
| 121 |
+
"acc": 0.662,
|
| 122 |
+
"num_correct": 662,
|
| 123 |
+
"num_pred": 1000
|
| 124 |
+
},
|
| 125 |
+
"VisualNews_t2i": {
|
| 126 |
+
"acc": 0.797,
|
| 127 |
+
"num_correct": 797,
|
| 128 |
+
"num_pred": 1000
|
| 129 |
+
},
|
| 130 |
+
"VisualNews_i2t": {
|
| 131 |
+
"acc": 0.831,
|
| 132 |
+
"num_correct": 831,
|
| 133 |
+
"num_pred": 1000
|
| 134 |
+
},
|
| 135 |
+
"MSCOCO_t2i": {
|
| 136 |
+
"acc": 0.802,
|
| 137 |
+
"num_correct": 802,
|
| 138 |
+
"num_pred": 1000
|
| 139 |
+
},
|
| 140 |
+
"MSCOCO_i2t": {
|
| 141 |
+
"acc": 0.783,
|
| 142 |
+
"num_correct": 783,
|
| 143 |
+
"num_pred": 1000
|
| 144 |
+
},
|
| 145 |
+
"NIGHTS": {
|
| 146 |
+
"acc": 0.687,
|
| 147 |
+
"num_correct": 687,
|
| 148 |
+
"num_pred": 1000
|
| 149 |
+
},
|
| 150 |
+
"WebQA": {
|
| 151 |
+
"acc": 0.91,
|
| 152 |
+
"num_correct": 910,
|
| 153 |
+
"num_pred": 1000
|
| 154 |
+
},
|
| 155 |
+
"FashionIQ": {
|
| 156 |
+
"acc": 0.302,
|
| 157 |
+
"num_correct": 302,
|
| 158 |
+
"num_pred": 1000
|
| 159 |
+
},
|
| 160 |
+
"Wiki-SS-NQ": {
|
| 161 |
+
"acc": 0.691,
|
| 162 |
+
"num_correct": 691,
|
| 163 |
+
"num_pred": 1000
|
| 164 |
+
},
|
| 165 |
+
"OVEN": {
|
| 166 |
+
"acc": 0.657,
|
| 167 |
+
"num_correct": 657,
|
| 168 |
+
"num_pred": 1000
|
| 169 |
+
},
|
| 170 |
+
"EDIS": {
|
| 171 |
+
"acc": 0.945,
|
| 172 |
+
"num_correct": 945,
|
| 173 |
+
"num_pred": 1000
|
| 174 |
+
},
|
| 175 |
+
"MSCOCO": {
|
| 176 |
+
"acc": 0.914,
|
| 177 |
+
"num_correct": 914,
|
| 178 |
+
"num_pred": 1000
|
| 179 |
+
},
|
| 180 |
+
"RefCOCO": {
|
| 181 |
+
"acc": 0.959,
|
| 182 |
+
"num_correct": 959,
|
| 183 |
+
"num_pred": 1000
|
| 184 |
+
},
|
| 185 |
+
"RefCOCO-Matching": {
|
| 186 |
+
"acc": 0.939,
|
| 187 |
+
"num_correct": 939,
|
| 188 |
+
"num_pred": 1000
|
| 189 |
+
},
|
| 190 |
+
"Visual7W-Pointing": {
|
| 191 |
+
"acc": 0.883,
|
| 192 |
+
"num_correct": 883,
|
| 193 |
+
"num_pred": 1000
|
| 194 |
+
}
|
| 195 |
+
},
|
| 196 |
+
"video": {
|
| 197 |
+
"K700": "DIR_N/A",
|
| 198 |
+
"SmthSmthV2": "DIR_N/A",
|
| 199 |
+
"HMDB51": "DIR_N/A",
|
| 200 |
+
"UCF101": "DIR_N/A",
|
| 201 |
+
"Breakfast": "DIR_N/A",
|
| 202 |
+
"MVBench": "DIR_N/A",
|
| 203 |
+
"Video-MME": "DIR_N/A",
|
| 204 |
+
"NExTQA": "DIR_N/A",
|
| 205 |
+
"EgoSchema": "DIR_N/A",
|
| 206 |
+
"ActivityNetQA": "DIR_N/A",
|
| 207 |
+
"DiDeMo": "DIR_N/A",
|
| 208 |
+
"MSR-VTT": "DIR_N/A",
|
| 209 |
+
"MSVD": "DIR_N/A",
|
| 210 |
+
"VATEX": "DIR_N/A",
|
| 211 |
+
"YouCook2": "DIR_N/A",
|
| 212 |
+
"QVHighlight": "DIR_N/A",
|
| 213 |
+
"Charades-STA": "DIR_N/A",
|
| 214 |
+
"MomentSeeker": "DIR_N/A"
|
| 215 |
+
},
|
| 216 |
+
"visdoc": {
|
| 217 |
+
"ViDoRe_arxivqa": "DIR_N/A",
|
| 218 |
+
"ViDoRe_docvqa": "DIR_N/A",
|
| 219 |
+
"ViDoRe_infovqa": "DIR_N/A",
|
| 220 |
+
"ViDoRe_tabfquad": "DIR_N/A",
|
| 221 |
+
"ViDoRe_tatdqa": "DIR_N/A",
|
| 222 |
+
"ViDoRe_shiftproject": "DIR_N/A",
|
| 223 |
+
"ViDoRe_syntheticDocQA_artificial_intelligence": "DIR_N/A",
|
| 224 |
+
"ViDoRe_syntheticDocQA_energy": "DIR_N/A",
|
| 225 |
+
"ViDoRe_syntheticDocQA_government_reports": "DIR_N/A",
|
| 226 |
+
"ViDoRe_syntheticDocQA_healthcare_industry": "DIR_N/A",
|
| 227 |
+
"ViDoRe_esg_reports_human_labeled_v2": "DIR_N/A",
|
| 228 |
+
"ViDoRe_biomedical_lectures_v2_multilingual": "DIR_N/A",
|
| 229 |
+
"ViDoRe_economics_reports_v2_multilingual": "DIR_N/A",
|
| 230 |
+
"ViDoRe_esg_reports_v2_multilingual": "DIR_N/A",
|
| 231 |
+
"VisRAG_ArxivQA": "DIR_N/A",
|
| 232 |
+
"VisRAG_ChartQA": "DIR_N/A",
|
| 233 |
+
"VisRAG_MP-DocVQA": "DIR_N/A",
|
| 234 |
+
"VisRAG_SlideVQA": "DIR_N/A",
|
| 235 |
+
"VisRAG_InfoVQA": "DIR_N/A",
|
| 236 |
+
"VisRAG_PlotQA": "DIR_N/A",
|
| 237 |
+
"ViDoSeek-page-fixed": "DIR_N/A",
|
| 238 |
+
"ViDoSeek-doc": "DIR_N/A",
|
| 239 |
+
"MMLongBench-page-fixed": "DIR_N/A",
|
| 240 |
+
"MMLongBench-doc": "DIR_N/A"
|
| 241 |
+
}
|
| 242 |
+
}
|
| 243 |
+
}
|