reports/vl/agentrewardbench.json
162 B · 7 lines · json Raw
1 {
2 "n": 1302,
3 "auroc": 0.9079788939829442,
4 "precision_at_0.5": 0.7507598784194529,
5 "recall_at_0.5": 0.6938202247191011,
6 "positive_rate": 0.27342549923195086
7 }