End-to-end Tool-use on ToolBench I1 v1
56.13SoPR
ToolLlama-2*
Updated 4d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.01 | 56.13 | 50.92 | |
2026.01 | 56.13 | 50.92 | |
2026.01 | 54.85 | 36.08 | |
2026.01 | 54.6 | 49.08 | |
2026.01 | 53.17 | 40.49 | |
2026.01 | 53.17 | 40.49 | |
2026.01 | 53.16 | - | |
2026.01 | 52.97 | 36.2 | |
2026.01 | 52.97 | 36.2 | |
2026.01 | 52.25 | - | |
2026.01 | 52.25 | 47.24 | |
2026.01 | 51.43 | 53.37 | |
2026.01 | 45.36 | 32.91 | |
2026.01 | 28.94 | 25.15 | |
2026.01 | 28.94 | 25.15 | |
2026.01 | 28.48 | 26.58 |