Tool Calling on In-domain (unseen)
57.24Exact Match (EM)
TInR-U
Updated 4d ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 57.24 | 74.83 | 62.76 | |
2026.04 | 55.86 | 72.59 | 60.52 | |
2026.04 | 51.72 | 67.41 | 59.83 | |
2026.04 | 51.38 | 67.41 | 57.76 | |
2026.04 | 48.45 | 68.79 | 52.93 | |
2026.04 | 46.38 | 59.48 | 51.9 | |
2026.04 | 45.69 | 60 | 51.9 | |
2026.04 | 36.38 | 51.21 | 40 | |
2026.04 | 33.28 | 43.45 | 34.83 | |
2026.04 | 26.38 | 44.14 | 41.38 |