Qwen3-8B-GRPO
| Method | Links | ||||
|---|---|---|---|---|---|
2026.01 | 100 | 95.3 | 62.4 | 2.25 | |
2026.01 | 100 | 94 | 61.7 | 2.22 | |
2026.01 | 100 | 93.8 | 60.4 | 2.31 | |
2026.01 | 100 | 86.2 | 50.1 | 3.71 | |
2026.01 | 100 | 66.9 | 37.6 | 4.74 | |
2026.01 | 100 | 95.3 | 62.4 | 2.25 | |
2026.01 | 100 | 94 | 61.7 | 2.22 | |
2026.01 | 100 | 93.8 | 60.4 | 2.31 | |
2026.01 | 100 | 97.3 | 60.3 | 1.82 | |
2026.01 | 100 | 97.1 | 60.4 | 1.85 | |
2026.01 | 100 | 86.2 | 50.1 | 3.71 | |
2026.01 | 99.8 | 93.1 | 60.8 | 2.34 | |
2026.01 | 99.8 | 82.9 | 47.8 | 3.78 | |
2026.01 | 99.8 | 81.8 | 40.9 | 3.72 | |
2026.01 | 99.8 | 93.1 | 60.8 | 2.34 | |
2026.01 | 99.8 | 82.9 | 47.8 | 3.78 | |
2026.01 | 99.8 | 81.8 | 40.9 | 3.72 | |
2026.01 | 99.6 | 88.9 | 52.2 | 3.3 | |
2026.01 | 99.3 | 86 | 53.1 | 3.89 | |
2026.01 | 99.3 | 58.9 | 44.8 | 4.86 | |
2026.01 | 99.3 | 88.7 | 52.2 | 3.3 | |
2026.01 | 99.3 | 58.9 | 44.8 | 4.86 | |
2026.01 | 99.1 | 56.7 | 34.5 | 5.08 | |
2026.01 | 99.1 | 54.9 | 42.6 | 5.97 | |
2026.01 | 99.1 | 56.7 | 34.5 | 5.08 | |
2026.01 | 98.9 | 61.1 | 32 | 4.98 | |
2026.01 | 98.9 | 31.6 | 46.8 | 8.06 | |
2026.01 | 97.8 | 86.2 | 47.8 | 3.15 | |
2026.01 | 97.8 | 77.8 | 40.1 | 4.36 | |
2026.01 | 97.8 | 86.2 | 47.8 | 3.15 | |
2026.01 | 96.7 | 75.8 | 50.9 | 4.23 | |
2026.01 | 94.4 | 71.6 | 36.2 | 4.41 | |
2026.01 | 94.2 | 76.9 | 49 | 3.92 | |
2026.01 | 93.8 | 60.9 | 46.9 | 4.81 | |
2026.01 | 93.8 | 60.9 | 46.9 | 4.81 | |
2026.01 | 93.1 | 49.8 | 26 | 6.04 | |
2026.01 | 88.9 | 53.6 | 35.4 | 6.32 | |
2026.01 | 85.6 | 52.4 | 18.3 | 5.63 | |
2026.01 | 84.2 | 70.7 | 19.2 | 3.23 | |
2026.01 | 84.2 | 70.7 | 19.2 | 3.23 | |
2026.01 | 62.9 | 62.7 | 52.5 | 0.83 | |
2026.01 | 55.3 | 40.4 | 25.6 | 2.48 |