Function Calling on ToolRL 80-prompt (held-out)
94Best@3
Max-at-K
Updated 12d ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2026.05 | 94 | 94.5 | 94.9 | 95.4 | 0.131 | |
2026.05 | 92.1 | 92.3 | 92.4 | 92.5 | 0.044 | |
2026.05 | 90.2 | 90.4 | 90.6 | 90.7 | 0.064 | |
2026.05 | 89.7 | 93.4 | 95 | 95.2 | 1.297 | |
2026.05 | 86.1 | 88.3 | 89.8 | 90.5 | 0.308 | |
2026.05 | 77.9 | 80.5 | 82.6 | 84.6 | 0.51 | |
2026.05 | 11.2 | 11.4 | 11.6 | 12.3 | 0.026 | |
2026.05 | 9.3 | 10.4 | 11.1 | 11.6 | 0.198 |