End-to-end Tool-use on ToolBench v1 (I2)
52.2SoPR
ToolGen*
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 52.2 | 62.26 | |
2026.01 | 49.96 | 61.32 | |
2026.01 | 49.21 | 53.77 | |
2026.01 | 45.13 | 42.45 | |
2026.01 | 45.13 | 42.45 | |
2026.01 | 44.03 | 48.11 | |
2026.01 | 44.03 | 48.11 | |
2026.01 | 41.19 | 53.77 | |
2026.01 | 40.41 | - | |
2026.01 | 40.41 | 52.83 | |
2026.01 | 24.69 | 30.19 | |
2026.01 | 24.69 | 30.19 |