Benchmark
BFCL Benchmark
What is BFCL?
Schema complexity and execution checking vary by version. Benchmark Radar tracks 2 reported scores for BFCL, cited by 4 source documents.
- Released
- 2024-02-26
- Evaluates
- tool use
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 2
Source provenance
- Original evidence https://gorilla.cs.berkeley.edu/leaderboard.html
BFCL links
BFCL results and reported scores
Model reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Qwen3-235B-A22B (Thinking) | Qwen | 70.8 | 2025-05-14 | evidence |
| Qwen3.5-397B-A17B | Qwen | 72.9 | 2026-02-16 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.
Which sources cite BFCL?
- Qwen3.5-397B-A17B Qwen, 2026-02-16
- Olmo 3 (7B and 32B) Ai2, 2025-11-20
- Qwen3 Qwen, 2025-05-14
- Llama 3.1 405B Meta, 2024-07-23