GRPO
| Method | Links | |||
|---|---|---|---|---|
2025.05 | 87.11 | - | - | |
2025.05 | 87.11 | - | - | |
2025.05 | 86.88 | - | - | |
2025.05 | 82.28 | - | - | |
2025.05 | 82.28 | - | - | |
2025.05 | 81.33 | - | - | |
2025.05 | 81.24 | - | - | |
2025.05 | 81.17 | - | - | |
2025.05 | 80.3 | - | - | |
2025.05 | 80.22 | - | - | |
2025.05 | 72.78 | - | - | |
2025.05 | 71.52 | - | - | |
2025.05 | 68.99 | - | - | |
2025.05 | 45.73 | - | - | |
2025.05 | 45.09 | - | - | |
2025.05 | 44.15 | - | - | |
2025.05 | 41.14 | - | - | |
2025.05 | 39.16 | - | - | |
2025.05 | 39 | - | - | |
2025.10 | - | 42.6 | 31.3 | |
2025.10 | - | 35.1 | 27.5 | |
2025.10 | - | 59.3 | 43.6 | |
2025.10 | - | 59.2 | 43.6 | |
2025.10 | - | 60.8 | 42.6 | |
2025.10 | - | 62.7 | 46.6 | |
2025.10 | - | 62.9 | 46.5 | |
2025.10 | - | 67.2 | 45 | |
2025.10 | - | 63.4 | 50.9 |