| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| CodeEditorBench | AdaPLD | Debug Success Rate3.04 | 33 | 1mo ago | |
| CanItEdit | Stable-DiffCoder-8B-Instruct | Pass@160 | 17 | 5mo ago | |
| Aider whole format | CodeLlama-7B-Instruct | Average Tries1.5 | 17 | 5mo ago | |
| EditBench Core set | Pass@166.67 | 13 | 4mo ago | ||
| CanItEdit original (test) | Pass@1 (Average)39.9 | 9 | 5mo ago | ||
| Aider-Polyglot | Accuracy61.7 | 6 | 5mo ago |