General Chat Evaluation on Arena-Hard
84Win Rate
VRM-PPO
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.03 | 84 | 82 | |
2026.03 | 70.8 | 71.9 | |
2026.03 | 69.5 | 70.1 | |
2026.03 | 65.5 | 57.2 | |
2026.03 | 65.5 | 54.9 | |
2026.03 | 62 | 53 | |
2026.03 | 61.9 | 56.6 | |
2026.03 | 60.4 | 51.8 | |
2026.03 | 60.4 | 71.9 | |
2026.03 | 56.2 | 53.7 | |
2026.03 | 55.3 | 48.9 | |
2026.03 | 54.6 | 48.3 | |
2026.03 | 54.6 | 48.8 | |
2026.03 | 51.7 | 48.2 | |
2026.03 | 49 | 47.2 | |
2026.03 | 43.9 | 44.1 |