Reward Modeling on PPE Preference ZH
82.3Accuracy
OpenRS
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 82.3 | 89.4 | |
| 79.6 | 84.3 | ||
2026.02 | 78.9 | 86.7 | |
2026.02 | 78.4 | 84.9 | |
2026.02 | 78.1 | 86.2 | |
2026.02 | 78 | - | |
2026.02 | 76.6 | 86.8 | |
2026.02 | 76.3 | - | |
| 75.3 | - | ||
2026.02 | 72.2 | - | |
2026.02 | 71.1 | - | |
2026.02 | 69.4 | 64.8 | |
2026.02 | 68.7 | 70.5 | |
2026.02 | 65.7 | 71.7 | |
| 62.2 | 67.1 | ||
2026.02 | 60.6 | 65 | |
2026.02 | 58.3 | 63.4 | |
| 57.6 | 67.3 | ||
2026.02 | 43.3 | 67.4 |