Reward Modeling on LMArena-like Benchmarks PPE Pref ZH, In-House QA, In-House Writing v1.0
82.3PPE Pref ZH Score
OpenRS
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.02 | 82.3 | 74.4 | 82.9 | 79.9 | |
2026.02 | 79.6 | 64 | 76.3 | 73.5 | |
2026.02 | 78.9 | 75.7 | 79 | 77.9 | |
2026.02 | 78.4 | 74.5 | 79.8 | 77.6 | |
2026.02 | 78.1 | 72.7 | 77.3 | 76 | |
2026.02 | 76.6 | 74.7 | 84.6 | 78.6 | |
2026.02 | 76.3 | 73.1 | 84.3 | 77.9 | |
2026.02 | 75.3 | 71.4 | 77.9 | 74.8 | |
2026.02 | 72.2 | 67.3 | 76.3 | 71.9 | |
2026.02 | 71.1 | 67.7 | 75.9 | 71.6 | |
2026.02 | 69.4 | 67.8 | 60.3 | 66.1 | |
2026.02 | 68.7 | 61.8 | 77.3 | 68.8 | |
2026.02 | 65.7 | 67.2 | 64.5 | 66 | |
2026.02 | 62.2 | 61.7 | 77.7 | 67 | |
2026.02 | 60.6 | 58.9 | 79.1 | 66.1 | |
2026.02 | 58.3 | 58.3 | 73.1 | 63.1 | |
2026.02 | 57.6 | 56.1 | 66.5 | 60 | |
2026.02 | 43.3 | 59.1 | 29.7 | 50.2 |