| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| BFCL out-of-domain | TInR-U | Exact Match38.06 | 9 | 4d ago | |
| In-domain unseen | TInR-U | EM75.86 | 9 | 4d ago | |
| In-domain (seen) | TInR-U | Exact Match (EM)85.95 | 9 | 4d ago | |
| BFCL multi-turn category (test) | TInR-U | Accuracy34.48 | 4 | 4d ago | |
| Tool Use Evaluation (test) | TInR-U | EM Accuracy78.3 | 3 | 4d ago | |
| ToolACE multi-turn (test) | TInR-U | Accuracy75.34 | 2 | 4d ago |