Tool Usage on BFCL Parallel v1
95.5Accuracy
THINKBRAKE
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.10 | 95.5 | -26.8 | |
2025.10 | 93.5 | - | |
2025.10 | 93 | -21.2 | |
2025.10 | 93 | - | |
2025.10 | 92 | - | |
2025.10 | 91 | -13 | |
2025.10 | 91 | -14.3 | |
2025.10 | 90 | - | |
2025.10 | 90 | -16.3 | |
2025.10 | 89.5 | -16.5 | |
2025.10 | 88.5 | -44.4 | |
2025.10 | 88 | -13.5 | |
2025.10 | 87.5 | - | |
2025.10 | 84.5 | 2.7 | |
2025.10 | 81 | -1.3 | |
2025.10 | 79.5 | -100 | |
2025.10 | 78 | -26.9 | |
2025.10 | 62 | -4 | |
2025.10 | 52.5 | - | |
2025.10 | 42 | -14.6 |