Tool Use on Extended BFCL Single
61.54File Accuracy
Claude-Sonnet-4.5
Updated 4d ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.04 | 61.54 | 52.63 | 85 | 84.62 | |
2026.04 | 53.85 | 52.63 | 85 | 84.62 | |
2026.04 | 53.85 | 15.79 | 55 | 61.54 | |
2026.04 | 46.15 | 5.26 | 70 | 30.77 | |
2026.04 | 46.15 | 26.32 | 50 | 69.23 | |
2026.04 | 38.46 | 47.37 | 90 | 92.31 | |
2026.04 | 38.46 | 47.37 | 95 | 100 | |
2026.04 | 38.46 | 31.58 | 50 | 53.85 | |
2026.04 | 30.77 | 21.05 | 65 | 46.15 | |
2026.04 | 23.08 | 10.53 | 65 | 23.08 | |
2026.04 | 23.08 | 21.05 | 65 | 30.77 | |
2026.04 | 15.38 | 21.05 | 45 | 46.15 |