Tool Usage on Meta-Tool Multiple
91.1Accuracy
THINKBRAKE
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.10 | 91.1 | -3 | |
2025.10 | 90.9 | -15.4 | |
2025.10 | 90.5 | - | |
2025.10 | 90.5 | -8.4 | |
2025.10 | 90.5 | - | |
2025.10 | 90.3 | -5.4 | |
2025.10 | 86.7 | -12.7 | |
2025.10 | 86.5 | -100 | |
2025.10 | 86.3 | -9 | |
2025.10 | 85.7 | -4.5 | |
2025.10 | 85.5 | - | |
2025.10 | 85.5 | -1.1 | |
2025.10 | 84.9 | - | |
2025.10 | 84.7 | -11.2 | |
2025.10 | 84.5 | -5.8 | |
2025.10 | 84.3 | - | |
2025.10 | 83.9 | 1.3 | |
2025.10 | 80.3 | - | |
2025.10 | 76.3 | -26.3 | |
2025.10 | 73.2 | -19.3 |