Tool Selection on APIGen sampled (test)
99.4Tool Selection F1 (2 calls)
TokMem (w/ adapt)
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2025.10 | 99.4 | 97.9 | 100 | 99.1 | |
2025.10 | 99.2 | 98.2 | 100 | 99.2 | |
2025.10 | 98.8 | 97.2 | 98.2 | 98.1 | |
2025.10 | 98.7 | 98.1 | 96.8 | 97.9 | |
2025.10 | 98.4 | 98 | 98.9 | 98.4 | |
2025.10 | 86.8 | 80.9 | 90.8 | 86.2 | |
2025.10 | 84.9 | 82 | 81.6 | 82.8 | |
2025.10 | 82.6 | 79.3 | 67.2 | 76.4 | |
2025.10 | 79.7 | 72.9 | 75.4 | 76 | |
2025.10 | 79.6 | 75.3 | 93 | 82.6 | |
2025.10 | 78.1 | 71.2 | 69.3 | 72.8 | |
2025.10 | 66.8 | 59.2 | 59.6 | 61.9 | |
2025.10 | 29.5 | 10.8 | 10.5 | 16.9 | |
2025.10 | 27.6 | 11.1 | 10.5 | 16.4 | |
2025.10 | 10.4 | 9.5 | 7 | 9 |