GRPO
| Method | Links | ||||
|---|---|---|---|---|---|
2025.09 | 0.3 | - | - | 0 | |
2025.09 | 1.7 | - | - | 0 | |
2025.09 | 3 | - | - | 0.3 | |
2025.09 | 5.2 | - | - | 0 | |
2025.09 | 5.7 | - | - | 0.3 | |
2025.09 | 6 | - | - | 0.3 | |
2025.09 | 8 | - | - | 0.3 | |
2025.09 | 8.7 | - | - | 0 | |
2025.09 | 11 | - | - | 0 | |
2025.09 | 11.4 | - | - | 2 | |
2025.09 | 18 | - | - | 0.7 | |
2025.09 | 20.7 | - | - | 0 | |
2025.09 | 24.3 | - | - | 4 | |
2025.09 | 56.1 | - | - | 25.3 | |
2025.09 | 56.1 | - | - | 25.3 | |
2025.09 | 69 | - | - | 45 | |
2025.09 | 72.4 | - | - | 56 | |
2025.09 | - | 69 | 45 | - | |
2025.09 | - | 0.3 | 0 | - | |
2025.09 | - | 6 | 0 | - | |
2025.09 | - | 8 | 0.3 | - | |
2025.09 | - | 7 | 0 | - | |
2025.09 | - | 5.7 | 0.3 | - |