Code Verification on MBPP (test)
100Mean Hit Rate
Oracle
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.06 | 100 | - | |
2026.06 | 88.2 | 17 | |
2026.06 | 83.7 | 15.1 | |
2026.06 | 80.3 | 11 | |
2026.06 | 72.8 | 5.3 | |
2026.06 | 67.1 | 3.4 | |
2026.06 | 66.1 | 5.1 | |
2026.06 | 66.1 | 5.6 | |
2026.06 | 65.6 | - | |
2026.06 | 63.6 | - | |
2026.06 | 63.1 | 4.3 | |
2026.06 | 62.2 | - | |
2026.06 | 61.4 | 6.7 | |
2026.06 | 61.2 | 3.4 | |
2026.06 | 61 | 6.5 | |
2026.06 | 59.7 | - | |
2026.06 | 59.2 | 8.1 | |
2026.06 | 55.1 | - |