| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| RepoBench-P 128K context | Score60 | 18 | 1mo ago | ||
| RepoEval (test) | RLCoder | Exact Match49.9 | 8 | 2mo ago | |
| RepoBench (test) | RLCoder | Exact-match Accuracy65.9 | 7 | 2mo ago | |
| CrossCodeEval (test) | Python EM35.9 | 5 | 3mo ago | ||
| CrossCodeEval | Python EM35.9 | 5 | 3mo ago |