Code Reasoning on Code Benchmarks HumanEval MBPP
72.29HumanEval
RASFT
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.06 | 72.29 | 58.33 | 65.31 | |
2026.06 | 71.57 | 55.44 | 63.51 | |
2026.06 | 71.46 | 56.32 | 63.89 | |
2026.06 | 69.28 | 53.29 | 61.29 | |
2026.06 | 66.12 | 51.29 | 58.71 | |
2026.06 | 65.05 | 56.5 | 60.78 | |
2026.06 | 64.33 | 56.43 | 60.38 | |
2026.06 | 63.15 | 56.09 | 59.62 | |
2026.06 | 60.33 | 47.98 | 54.16 | |
2026.06 | 55.87 | 48.39 | 52.13 | |
2026.06 | 28.39 | 34.87 | 31.63 | |
2026.06 | 21.8 | 26.49 | 24.15 | |
2026.06 | 20.73 | 29.13 | 24.93 | |
2026.06 | 20.39 | 41.59 | 30.99 | |
2026.06 | 19.74 | 23.65 | 21.7 | |
2026.06 | 19.55 | 33.4 | 26.48 | |
2026.06 | 17.95 | 25.98 | 21.97 | |
2026.06 | 8.35 | 9.54 | 8.95 |