Function Calling on ACEBench Normal (test)
53Summary Score
CKD+Sim-RL
Updated 4d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2026.02 | 53 | 69.3 | 35 | 32 | 62 | 20 | |
2026.02 | 44.4 | 59.3 | 26.5 | 26 | 50 | 22 | |
2026.02 | 40.1 | 54 | 21.5 | 23 | 46 | 22 | |
2026.02 | 39.3 | 53.3 | 23.5 | 21 | 52 | 10 | |
2026.02 | 39 | 55 | 21 | 19 | 48 | 10 | |
2026.02 | 38.9 | 53 | 21.5 | 21 | 46 | 18 | |
2026.02 | 36.8 | 52.3 | 16 | 16 | 42 | 22 | |
2026.02 | 29.4 | 45 | 12.5 | 10 | 34 | 4 | |
2026.02 | 28.7 | 42.3 | 14 | 9 | 34 | 10 | |
2026.02 | 27.2 | 37.7 | 19.5 | 10 | 36 | 6 | |
2026.02 | 2.1 | 1.7 | 0.5 | 0 | 14 | 0 |