Python Programming on MBPP
46.3MBPP Score
Qwen3-4B + FBS-Full (ours)
Updated 9d ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.01 | 46.3 | 532 | 0.7 | 36 | - | |
2026.04 | 38.2 | - | - | - | 46.1 | |
2026.04 | 30.18 | - | - | - | 37.48 | |
2026.04 | 29.27 | - | - | - | 37.54 | |
2026.04 | 21.88 | - | - | - | 30.6 | |
2026.04 | 21.8 | - | - | - | 33.45 | |
2026.04 | 19.41 | - | - | - | 28.8 | |
2026.04 | 16.76 | - | - | - | 26.94 | |
2026.04 | 14.32 | - | - | - | 22.56 | |
2026.04 | 12.12 | - | - | - | 24.54 | |
2026.04 | 12 | - | - | - | 24.85 | |
2026.04 | 9.24 | - | - | - | 16.96 | |
2026.04 | 6.32 | - | - | - | 16.97 | |
2026.04 | 6.31 | - | - | - | 15.1 | |
2026.04 | 3.41 | - | - | - | 14.85 | |
2026.04 | 1.02 | - | - | - | 11.77 | |
2026.04 | 0 | - | - | - | 3.88 | |
2026.04 | 0 | - | - | - | 1.9 | |
2026.04 | 0 | - | - | - | 6.07 | |
2026.04 | 0 | - | - | - | 9.69 | |
2026.04 | 0 | - | - | - | 12.1 |