Conference paper · 2025
The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models
| Venue | Proceedings of the 42nd International Conference on Machine Learning |
|---|---|
| URL | https://proceedings.mlr.press/v267/patil25a.html |
| Topics | ReplicHAI / Agent Evals / 06 Tool use, function calling & MCP |
| Tags | agent-eval |
| pages | 48371-48392 |
| publisher | PMLR |
| volume | 267 |
Abstract
Measures: Function calling: single, parallel, multi-turn, agentic. Metric: AST/exec accuracy.
BibTeX
@inproceedings{patil_berkeley_2025,
title = {The {Berkeley} {Function} {Calling} {Leaderboard} ({BFCL}): {From} {Tool} {Use} to {Agentic} {Evaluation} of {Large} {Language} {Models}},
volume = {267},
url = {https://proceedings.mlr.press/v267/patil25a.html},
abstract = {Measures: Function calling: single, parallel, multi-turn, agentic. Metric: AST/exec accuracy.},
publisher = {PMLR},
author = {Patil, Shishir G. and Mao, Huanzhi and Yan, Fanjia and Ji, Charlie Cheng-Jie and Suresh, Vishnu and Stoica, Ion and Gonzalez, Joseph E.},
year = {2025},
keywords = {agent-eval},
pages = {48371--48392},
}