OptPO-GRPO
| Method | Links | |||||
|---|---|---|---|---|---|---|
2025.12 | 56.8 | 77.1 | 57.8 | - | 49.06 | |
2025.12 | 56 | 79.5 | 57.8 | - | 43.5 | |
2025.12 | 54.3 | 79.5 | 55.4 | - | - | |
2025.12 | 53.2 | 79.5 | 55.4 | - | 41.66 | |
2025.12 | 52.9 | 80.7 | 55.4 | - | - | |
2025.12 | 52.1 | 78.3 | 54.2 | - | - | |
2025.12 | 48.5 | 81.9 | 54.2 | - | 26.93 | |
2025.12 | 48.1 | 83.1 | 55.4 | - | - | |
2025.12 | 48.1 | 83.1 | 53 | - | 26.8 | |
2025.12 | 47.7 | 83.1 | 54.2 | - | - | |
2025.12 | 39.3 | 81.9 | 49.4 | - | - | |
2025.12 | 38.3 | 81.9 | 44.6 | - | 27.42 | |
2025.12 | 17.1 | 54.2 | 22.9 | - | 41.76 | |
2025.12 | 15.2 | 55.4 | 16.9 | - | 78.36 | |
2025.12 | 14.9 | 51.8 | 18.1 | - | - | |
2025.12 | 13.9 | 55.4 | 19.3 | - | - | |
2025.12 | 11.4 | 54.2 | 16.9 | - | - | |
2025.12 | 11 | 51.8 | 13.3 | - | 18.96 |