Benchmark
BFCL Benchmark
What is BFCL?
The Berkeley Function Calling Leaderboard (BFCL) is the first comprehensive and executable function call evaluation dedicated to assessing Large Language…
- Modality
- text
- Evaluates
- reasoning, general, tool calling
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 11
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/bfcl?top_n=500
BFCL results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Llama 3.1 405B Instruct | Meta | 0.885 | 2024-07-23 | evidence |
| Llama 3.1 70B Instruct | Meta | 0.848 | 2024-07-23 | evidence |
| Llama 3.1 8B Instruct | Meta | 0.761 | 2024-07-23 | evidence |
| Nova 2 Sonic | Amazon | 0.745 | 2025-12-02 | evidence |
| Nova Lite | Amazon | 0.666 | 2024-11-20 | evidence |
| Nova Micro | Amazon | 0.562 | 2024-11-20 | evidence |
| Nova Pro | Amazon | 0.684 | 2024-11-20 | evidence |
| Qwen3 235B A22B | Qwen | 0.708 | 2025-04-29 | evidence |
| Qwen3 30B A3B | Qwen | 0.691 | 2025-04-29 | evidence |
| Qwen3 32B | Qwen | 0.703 | 2025-04-29 | evidence |
| QwQ-32B | Qwen | 0.664 | 2025-03-05 | 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.