ModelRefs / BFCL (Berkeley Function Calling Leaderboard) — AI Glossary
BFCL (Berkeley Function Calling Leaderboard) — AI Glossary
A benchmark evaluating LLMs on their ability to correctly call functions — including simple, parallel, nested, and multi-turn scenarios.
Overview
BFCL (UC Berkeley, 2024) tests function-calling accuracy across multiple languages and call types. It is the primary leaderboard for comparing tool-use quality across providers. Updated regularly with new function schemas.
Reference details
| Topic | evaluation |
|---|---|
| Also known as | Berkeley Function Calling Leaderboard |
| Last reviewed | 2026-06-24 |
Related terms
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to BFCL (Berkeley Function Calling Leaderboard) — AI Glossary.
Frequently asked questions
What is BFCL (Berkeley Function Calling Leaderboard)?
A benchmark evaluating LLMs on their ability to correctly call functions — including simple, parallel, nested, and multi-turn scenarios.
Is BFCL (Berkeley Function Calling Leaderboard) the same as Berkeley Function Calling Leaderboard?
Yes — Berkeley Function Calling Leaderboard are common aliases for BFCL (Berkeley Function Calling Leaderboard).
What concepts are related to BFCL (Berkeley Function Calling Leaderboard)?
Closely related concepts include evaluation benchmark, function calling, tool use.