BFCL-V4 A
AI benchmark · Tool Use
What is BFCL-V4?
BFCL V4 measures how accurately LLMs call functions (tools), covering single-turn, multi-turn, and agentic tasks like web search and memory, along with hallucination measurement.
General capability mostly
“evaluates the LLM's ability to call functions (aka tools) accurately.”
gorilla.cs.berkeley.edu/leaderboard ↗
Who built BFCL-V4
Led by UC Berkeley (Gorilla project).
Lineage
Benchmarks this one is built on and built from: versions, subsets, extensions and the indexes that combine them.
Built on
BFCL v3 earlier version
Tier A
Widely used: a lab reports it, or 50 or more models are scored on it.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- 104 models scored
- in curated RL directories (2 pts)
On X · well regarded, low buzz, from 10 posts about BFCL-V4 in the last month
BFCL v4 shows up mainly as a standard line in model release tables, with some praise for its multi-turn focus and one report of reward hacks in it.
How we got to tier A
- Adoption: 104 models scored. Tier A.
- On X: well regarded, low buzz. “BFCL v4 shows up mainly as a standard line in model release tables, with some praise for its multi-turn focus and one report of reward hacks in it.” No move.
- In curated RL directories: 2 points, a floor of C.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where BFCL-V4 sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-11-07 snapshot.