Multi-turn tool use on Xbench
75.1Pass@1
WebAnchor-30B
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 75.1 | 85 | |
2026.01 | 72 | 88 | |
2026.01 | 71 | - | |
2026.01 | 71 | 84 | |
2026.01 | 66.7 | - | |
2026.01 | 64.6 | - | |
2026.01 | 53.3 | - | |
2026.01 | 50 | - | |
2026.01 | 45 | 66 | |
2026.01 | 40.7 | 56 | |
2026.01 | 39 | - | |
2026.01 | 37.7 | 56 | |
2026.01 | 37.7 | 52 | |
2026.01 | 34.7 | 55 | |
2026.01 | 34.3 | - | |
2026.01 | 31.6 | 55 | |
2026.01 | 24 | - | |
2026.01 | 4 | - |