| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Code Generation | xCodeEval | Pass@181.13 | 36 | |
| Code Generation | xCodeEval (sample 500) | Accuracy (Easy)0.831 | 17 | |
| Code Generation | xCodeEval Rust | Pass@123.6 | 3 | |
| Code Generation | xCodeEval C | Pass@124.5 | 3 | |
| Code Generation | xCodeEval Python | Pass@127.4 | 3 |