| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| LiveCodeBench | CVeDRL | Pass@139.31 | 32 | 5mo ago | |
| MBPP+ | CVeDRL | Pass@176.93 | 32 | 5mo ago | |
| HumanEval+ | CVeDRL | Pass@187.05 | 32 | 5mo ago | |
| MBPP (test) | Mean Hit Rate100 | 18 | 1mo ago | ||
| CLEVER | Base Goedel | Success Count70 | 8 | 2mo ago | |
| VERINA | IDS | Success Count176 | 8 | 2mo ago | |
| DAFNYBENCH | Solver backed | Success Count372 | 2 | 2mo ago |