| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TerminalBench 2.0 | Accuracy57.8 | 29 | 1mo ago | ||
| TerminalBench 1.0 | Accuracy54.38 | 29 | 1mo ago | ||
| CRUST-Bench | TACO | Accuracy48.05 | 2 | 1mo ago | |
| DevEval | TACO | Accuracy39.74 | 2 | 1mo ago | |
| CompileBench | Accuracy75 | 2 | 1mo ago | ||
| SWE-Bench Lite | TACO | Accuracy57.12 | 2 | 1mo ago |
