BFCL v2
Berkeley Function Calling Leaderboard (BFCL) v2 is a comprehensive benchmark for evaluating large language models' function calling capabilities. It features 2,251 question-function-answer pairs with enterprise and OSS-contributed functions, addressing data contamination and bias through live, user-contributed scenarios. The benchmark evaluates AST accuracy, executable accuracy, irrelevance detection, and relevance detection across multiple programming languages (Python, Java, JavaScript) and includes complex real-world function calling scenarios with multi-lingual prompts.
5rows
scoreprimary metric
2026-05-06sampled
Metadata
Metrics
Score, Normalized Score
| Rank | Subject | Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | Llama 3.3 70B Instruct | 0.77 |  Llama 3.3 70B Instruct meta-llama-llama-3.3-70b-instruct | Self-reported | 2026-05-06 |
| 2 | Llama 3.1 Nemotron Ultra 253B v1 | 0.74 | — | Self-reported | 2026-05-06 |
| 3 | Llama-3.3 Nemotron Super 49B v1 | 0.74 | — | Self-reported | 2026-05-06 |
| 4 | Llama 3.2 3B Instruct | 0.67 | Llama 3.2 3B Instruct meta-llama-llama-3.2-3b-instruct | Self-reported | 2026-05-06 |
| 5 | Llama 3.1 Nemotron Nano 8B V1 | 0.64 | — | Self-reported | 2026-05-06 |
No matching rows.