Berkeley Function Calling Leaderboard (BFCL)
Leaderboard that tests how accurately models call functions and tools, from single calls to multi-turn agentic use.
Reference by Gorilla project, UC Berkeley
IndexedApache-2.0★ 13,058
About
Whether a model produces correct function calls (single, parallel, multi-turn), knows when not to call, and handles agentic tool tasks.
Use cases: llm-evaluation
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
About the benchmark
- Benchmark site
- gorilla.cs.berkeley.edu/leaderboard.html
- Current version
- V4gorilla.cs.berkeley.edu
- Maintainer
- Gorilla project, UC Berkeleygorilla.cs.berkeley.edu
- Launched
- 2024-02-26github.com
- Leaderboard
- gorilla.cs.berkeley.edu/leaderboard.html
We link to the official leaderboard instead of copying scores. Benchmarks get gamed and saturate; we never use them to rank listings.
Signals
- Stars
- 13,058
- Forks
- 1,414
- Open issues
- 166
- Last commit
- Mar 23, 2026 (7 months ago)
- Last release
- Jul 17, 2025 (1 year ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- V4
- License
- Apache-2.0
- Repository
- github.com/ShishirPatil/gorilla
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Cite this page
Berkeley Function Calling Leaderboard (BFCL) benchmark. Agent Mart. https://agentmart.dev/reference/berkeley-function-calling-leaderboard (last updated 2026-10-24)