Constrained GRPO, ScAdv
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
2026.02 | 0.957 | 0.928 | 0.989 | 0.998 | 0.796 | 0.977 | 0.774 | 3.361 | |
2026.02 | 0.955 | 0.887 | 0.987 | 0.993 | 0.868 | 0.976 | 0.743 | 3.344 | |
2026.02 | 0.953 | 0.789 | 0.978 | 0.993 | 0.836 | 0.976 | 0.651 | 2.539 | |
2026.02 | 0.944 | 0.988 | 1 | 0.995 | 1 | 0.877 | - | - | |
| 0.932 | 0.765 | 0.971 | 0.993 | 0.89 | 0.976 | 0.623 | 3.495 | ||
2026.02 | 0.908 | 0.661 | 0.9 | 0.989 | 0.954 | 0.973 | 0.49 | 7.172 | |
2026.02 | 0.897 | 0.8 | 0.947 | 0.99 | 0.944 | 0.978 | 0.612 | 6.9 | |
2026.02 | 0.891 | 0.625 | 0.876 | 0.989 | 0.968 | 0.976 | 0.445 | 9.05 | |
| 0.887 | 0.643 | 0.887 | 0.987 | 0.967 | 0.978 | 0.463 | 8.509 |