reports/vl/vl_rewardbench.json
296 B · 14 lines · json Raw
1 {
2 "n": 1247,
3 "seconds": 135.443541765213,
4 "overall": 74.33841218925421,
5 "general": 48.61878453038674,
6 "hallucination": 81.84245660881176,
7 "reasoning": 71.29337539432177,
8 "macro": 67.25153884450675,
9 "ci95": [
10 71.85244587008822,
11 76.74418604651163
12 ],
13 "order_agree": 84.04170008019246
14 }