Reward Modeling on RewardBench 2
93.4L-Acc
GPT-5-chat
Updated 1mo ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.02 | 93.4 | 10.3 | 83.7 | - | - | |
2026.02 | 93.1 | 5.1 | 88.3 | - | - | |
2026.02 | 92.6 | 3.4 | 89.4 | - | - | |
2026.02 | 92 | 1.7 | 90.4 | - | - | |
2026.02 | 92 | 14.6 | 78.5 | - | - | |
2026.02 | 91.9 | 18.9 | 74.5 | - | - | |
2026.02 | 91.6 | 9.4 | 83 | - | - | |
2026.02 | 90.6 | 16.2 | 75.9 | - | - | |
2026.02 | 90.2 | 13.9 | 77.7 | - | - | |
2026.02 | 90.1 | 4.8 | 85.7 | - | - | |
2026.02 | 89.8 | 21.7 | 70.3 | - | - | |
2026.02 | 89.2 | 25.9 | 66.1 | - | - | |
2026.02 | 88.5 | 36.7 | 56 | - | - | |
2026.02 | 88.1 | 29 | 62.5 | - | - | |
2026.02 | 87.9 | 20.1 | 70.2 | - | - | |
2026.02 | 87.8 | 19.3 | 70.9 | - | - | |
2026.02 | 87.1 | 18.3 | 71.2 | - | - | |
2026.02 | 85.3 | 27.4 | 61.9 | - | - | |
2026.02 | 84.2 | 25 | 63.2 | - | - | |
2026.02 | 82.7 | 24.6 | 62.4 | - | - | |
2025.07 | - | - | - | 76.5 | - | |
2025.07 | - | - | - | 67.2 | - | |
2025.07 | - | - | - | 57.4 | - | |
2025.07 | - | - | - | 66.6 | - | |
| - | - | - | 59.7 | - | ||
2025.07 | - | - | - | 78.1 | - | |
2025.07 | - | - | - | 69.8 | - | |
2025.07 | - | - | - | 71 | - | |
2026.02 | - | - | - | - | 70.1 | |
2026.02 | - | - | - | - | 69.3 | |
2026.02 | - | - | - | - | 69.3 | |
2026.02 | - | - | - | - | 70.1 | |
2026.02 | - | - | - | - | 69.3 |