Benchmark · Agent tasks

Berkeley Function Calling Leaderboard (BFCL)

Whether a model calls functions correctly: simple, parallel and multi-turn calls, knowing when no function fits, web search and memory tasks, run by the Berkeley team on every model, with native function calling and with prompting as separate rows.

Score
% overall accuracy, higher is better
Run by
UC Berkeley (Gorilla)
Status
Stale, newest result 16 December 2025, nothing new in six months
Updated
irregular
Data
the published file, Apache-2.0, read 20 November 2026
Method
gorilla.cs.berkeley.edu/leaderboard.html

Results

5 models we list, each at its best setting, best first.

#ModelScoreRangeWho ran itSettingDate
1Qwen3-30B-A3B-Instruct-2507 C41.4%Independentmode FC2025-12-16source
2Qwen3-4B-Instruct-2507 C35.7%Independentmode FC2025-12-16source
3Command R7B B32.1%Independentmode FC2025-12-16source
4Llama 3.3 70B B31.9%Independentmode FC2025-12-16source
5Amazon Nova 2 Lite A27.1%Independentmode FC2025-12-16source
Every setting, 7 rows
ModelAs the leaderboard names itScoreWho ran itSettingDate
Qwen3-30B-A3B-Instruct-2507Qwen3-30B-A3B-Instruct-250741.4%Independentmode FC2025-12-16source
Qwen3-30B-A3B-Instruct-2507Qwen3-30B-A3B-Instruct-250736.7%Independentmode Prompt2025-12-16source
Qwen3-4B-Instruct-2507Qwen3-4B-Instruct-250735.7%Independentmode FC2025-12-16source
Qwen3-4B-Instruct-2507Qwen3-4B-Instruct-250735.5%Independentmode Prompt2025-12-16source
Command R7BCommand R7B32.1%Independentmode FC2025-12-16source
Llama 3.3 70BLlama-3.3-70B-Instruct31.9%Independentmode FC2025-12-16source
Amazon Nova 2 LiteAmazon-Nova-2-Lite-v1:027.1%Independentmode FC2025-12-16source

A rank is among the models we list with a result, not a place on the whole leaderboard, and a model offered by several hosts is shown once, on its own listing. These results don't move our grades. Data: Berkeley Function Calling Leaderboard, UC Berkeley (Gorilla), Apache 2.0, Apache-2.0.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.