Tool Usage on BFCL Multi-Parallel v2
87.5Accuracy
THINKBRAKE
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.10 | 87.5 | -18.9 | |
2025.10 | 79.2 | - | |
2025.10 | 75 | -66.5 | |
2025.10 | 75 | -11.1 | |
2025.10 | 75 | -10.2 | |
2025.10 | 70.8 | - | |
2025.10 | 70.8 | - | |
2025.10 | 70.8 | - | |
2025.10 | 70.8 | -4.9 | |
2025.10 | 62.5 | -10.9 | |
2025.10 | 62.5 | -7.6 | |
2025.10 | 62.5 | -14.3 | |
2025.10 | 58.3 | - | |
2025.10 | 58.3 | -11.9 | |
2025.10 | 58 | -13.3 | |
2025.10 | 45.8 | -100 | |
2025.10 | 29.2 | -43.8 | |
2025.10 | 29.2 | - | |
2025.10 | 20.8 | 11 | |
2025.10 | 16.7 | -6 |