Tool Usage on Meta-Tool Single
77.7Accuracy
Phi-4-Reasoning
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.10 | 77.7 | - | |
2025.10 | 77.2 | -2.5 | |
2025.10 | 76.6 | -8.5 | |
2025.10 | 74.3 | - | |
2025.10 | 72.7 | -1.4 | |
2025.10 | 72.5 | -3.1 | |
2025.10 | 72.4 | -20.6 | |
2025.10 | 70.8 | -25.8 | |
2025.10 | 69.7 | - | |
2025.10 | 68.9 | 0.1 | |
2025.10 | 67.4 | -100 | |
2025.10 | 66.3 | -1.6 | |
2025.10 | 64.9 | 0.6 | |
2025.10 | 64.8 | - | |
2025.10 | 64.4 | -1.5 | |
2025.10 | 63.8 | 3.6 | |
2025.10 | 63.4 | -7.4 | |
2025.10 | 63.3 | - | |
2025.10 | 63.2 | - | |
2025.10 | 61.2 | -2.4 |