BFCL-v4 — Results
| Rank | Model | Score |
|---|---|---|
| 1 | spark-x2-6-4b | 71.8 |
| 2 | lfm3-1-7b | 71.39 |
| 3 | clover-35b-a3b-preview | 67.9 |
| 4 | minicpm5-2b | 66.6 |
| 5 | spark-x2-5-4b | 65.1 |
| 6 | spark-x2-5-4b | 65.1 |
| 7 | lfm2-5-24b-a2b | 65.01 |
| 8 | kolibri-1 | 61.4 |
| 9 | granite-4-2-30b | 61.39 |
| 10 | raon-1-mini-preview | 59.8 |
| 11 | lfm2-5-2-6b | 56.88 |
| 12 | granite-4-2-3b | 52.41 |
| 13 | k2-horizon-3-7b | 50.9 |
| 14 | granite-4-2-8b | 50.29 |
| 15 | spark-x2-5-1-7b | 46.9 |
| 16 | spark-x2-5-1-7b | 46.9 |
| 17 | lfm2-5-vl-3b | 32.5 |
| 18 | k2-horizon-0-9b | 28 |
B
BFCL-v4 — Evaluations
1 phaseActive
No evaluations yet for this benchmark.