reasoning benchmark
BFCL
The Berkeley Function Calling Leaderboard (BFCL) is the first comprehensive and executable function call evaluation dedicated to assessing Large Language Models' ability to invoke functions. It evaluates serial and parallel function calls across multiple programming languages (Python, Java, JavaScript, REST API) using a novel Abstract Syntax Tree (AST) evaluation method. The benchmark consists of over 2,000 question-function-answer pairs covering diverse application domains and complex use cases including multiple function calls, parallel function calls, and multi-turn interactions.
Updated Aug 7, 2026
Published models11
Registry coverage11
MetricScore
EvidenceB
BFCL leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | ME | 88.5% | 100.0% | 11 | C | |
| 2 | ME | 84.8% | 90.0% | 11 | C | |
| 3 | ME | 76.1% | 80.0% | 11 | C | |
| 4 | AM Nova 2 SonicAmazon | 74.5% | 70.0% | 11 | C | |
| 5 | AC | 70.8% | 60.0% | 11 | C | |
| 6 | AC | 70.3% | 50.0% | 11 | C | |
| 7 | AC | 69.1% | 40.0% | 11 | C | |
| 8 | AMNova ProAmazon | 68.4% | 30.0% | 11 | C | |
| 9 | AMNova LiteAmazon | 66.6% | 20.0% | 11 | C | |
| 10 | AC | 66.4% | 10.0% | 11 | C | |
| 11 | AMNova MicroAmazon | 56.2% | 0.0% | 11 | C |
Score distribution
Top published rows on the benchmark's original scale.
BFCL highlights
The top published results on this benchmark's own scale.
What is BFCL?
Definition and scoring fields from the benchmark registry.
The Berkeley Function Calling Leaderboard (BFCL) is the first comprehensive and executable function call evaluation dedicated to assessing Large Language Models' ability to invoke functions. It evaluates serial and parallel function calls across multiple programming languages (Python, Java, JavaScript, REST API) using a novel Abstract Syntax Tree (AST) evaluation method. The benchmark consists of over 2,000 question-function-answer pairs covering diverse application domains and complex use cases including multiple function calls, parallel function calls, and multi-turn interactions.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- BFCL
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- bfcl|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about BFCL.
Which model scores highest on BFCL?
Llama 3.1 405B Instruct is currently ranked first with 88.5%.
What does BFCL measure?
The Berkeley Function Calling Leaderboard (BFCL) is the first comprehensive and executable function call evaluation dedicated to assessing Large Language Models' ability to invoke functions. It evaluates serial and parallel function calls across multiple programming languages (Python, Java, JavaScript, REST API) using a novel Abstract Syntax Tree (AST) evaluation method. The benchmark consists of over 2,000 question-function-answer pairs covering diverse application domains and complex use cases including multiple function calls, parallel function calls, and multi-turn interactions.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
11 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is marked as eligible for the current LLMBoard capability methodology.