Public KG record
BFCL v4
Recorded overview
Tool calling benchmark score moved from 20.5 to 32.5.
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Benchmarks: CLM-8B 工具调用成功率为 95.2%
- Benchmarks: CLM-8B 延迟为 76.8 ms
Evidence coverage
The KG currently records 6 known information dimensions and has 12 undocumented dimensions, linked to 7 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- CLM-8B — evaluated on
- Kolibri — evaluated on
- LFM2.5-2.6B — evaluated on
- LFM2.5-VL-3B — evaluated on
- Needle 2 — evaluated on