| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| AppWorld | A-Evolve | TGC90 | 28 | 3mo ago | |
| TableBench | A³ | Pass@343 | 9 | 23d ago | |
| ShellOps | A³ | Pass@30.462 | 9 | 23d ago | |
| EHRCon | RetroAgent | Pass@379.1 | 9 | 23d ago | |
| DataBench | A³ | Pass@392.7 | 9 | 23d ago | |
| AB-DB | A³ | Pass@351.1 | 9 | 23d ago | |
| AB-OS | ReACT | Pass@379.7 | 9 | 23d ago | |
| AppWorld (test-n) | CLEAR | TGC Average81.15 | 4 | 1mo ago |