Multi-hop tool use on ToolHop
46.16Answer Correctness
MatchTIR (KM)
Updated 4d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.01 | 46.16 | |
2026.01 | 45.8 | |
2026.01 | 43.32 | |
2026.01 | 42.55 | |
2026.01 | 42.55 | |
2026.01 | 42.21 | |
2026.01 | 41.95 | |
2026.01 | 41.24 | |
2026.01 | 40.64 | |
2026.01 | 38.63 | |
2026.01 | 37.25 | |
2026.01 | 36.72 | |
2026.01 | 35.68 | |
2026.01 | 32.93 | |
2026.01 | 31.63 | |
2026.01 | 30.28 |