GRPO(120-Steps)
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
2026.03 | 100 | 95.2 | 80.8 | 88.9 | 78.6 | 88.3 | 92.9 | |
2026.03 | 97.6 | 95.8 | 100 | 88.9 | 90 | 91.7 | 95.3 | |
2026.03 | 97.1 | 100 | 75 | 87.5 | 100 | 78.6 | 90.6 | |
2026.03 | 96.4 | 57.1 | 96.2 | 85.7 | 72.2 | 95.3 | 85.2 | |
2026.03 | 94.3 | 90.6 | 92 | 83.3 | 93.7 | 80 | 89.1 | |
2026.03 | 93.8 | 94.7 | 95.5 | 77.8 | 95 | 72 | 87.8 | |
2026.03 | 92.9 | 100 | 95.2 | 80 | 90.9 | 86.7 | 92.2 | |
2026.03 | 90 | 92.3 | 52 | 63.6 | 42.9 | 40.9 | 67.2 | |
2026.03 | 89.7 | 77.8 | 85.7 | 91.6 | 86.7 | 69.6 | 83.6 | |
2026.03 | 89.5 | 60 | 64.9 | 36.3 | 50 | 26.3 | 62.5 | |
2026.03 | 89.4 | 72.4 | 66.7 | 54.5 | 60 | 50 | 72.7 | |
2026.03 | 88.6 | 75 | 54.2 | 66.7 | 60 | 52.6 | 69.6 | |
2026.03 | 88.3 | 73.3 | 76 | 83.3 | 81.3 | 40 | 75 | |
2026.03 | 78.1 | 56.1 | 65 | 54.8 | 31 | 26.9 | 54.7 | |
2026.03 | 73.5 | 46.6 | 48 | 61.1 | 62.5 | 20 | 53.9 | |
2026.03 | 64.3 | 19.1 | 23.1 | 64.3 | 33.3 | 61.9 | 43.8 | |
2026.03 | 53.6 | 28.6 | 46.2 | 71.4 | 55.5 | 38.1 | 47.7 | |
2026.03 | 50 | 9.5 | 0 | 2.1 | 11.1 | 4.8 | 17.2 | |
2026.03 | 17.9 | 4.8 | 3.8 | 64.3 | 0 | 5.3 | 12.5 |