Tool Use on ToolHop
54.87Answer Correctness
HarnessForge
Updated 1d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.06 | 54.87 | 74.05 | |
2026.06 | 52.82 | 68.1 | |
2026.06 | 51.28 | 75.62 | |
2026.06 | 50.77 | 72.75 | |
2026.06 | 49.74 | 66.41 | |
2026.06 | 48.72 | 72.2 | |
2026.06 | 47.39 | 59.31 | |
2026.06 | 46.15 | 64.87 | |
2026.06 | 45.13 | 63.9 | |
2026.06 | 44.62 | 58.74 | |
2026.06 | 44.62 | 51.8 | |
2026.06 | 42.05 | 51.8 | |
2026.06 | 42.05 | 61.32 | |
2026.06 | 40 | 44.99 | |
2026.06 | 32.82 | 54.12 | |
2026.06 | 31.28 | 43.81 | |
2026.06 | 30.77 | 41.22 | |
2026.06 | 29.23 | 39.46 |