Tool Usage on Real-world tool usage
90Success Rate
Compose by Focus
Updated 26d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2025.09 | 90 | |
2026.05 | 67.8 | |
2025.09 | 60 | |
2026.05 | 53.4 | |
2026.05 | 52.8 | |
2026.05 | 51.3 | |
2026.05 | 48.7 | |
2026.05 | 45.3 | |
2025.09 | 40 | |
2026.05 | 38.2 | |
2026.05 | 35.1 | |
2026.05 | 28.4 | |
2025.09 | 7.5 |