The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models

By Shishir G. Patil, Huanzhi Mao, Fanjia Yan, Charlie Cheng-Jie Ji, Vishnu Suresh, Ion Stoica, Joseph Gonzalez. International Conference on Machine Learning, 2025

390 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/d67976e4cd3ddc541172455c854c2be76d15baae

Citations in the corpus

• GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models (2025, unknown): “5 in two aspects: TAU-bench [48] (including retail and airline domains) and Berkeley Function Call Leaderboard V3 (BFCL V3) [26], which measures the model’s ability to call user-defined functions to respond to users’ queries.”
• Qwen3-VL Technical Report (2025, unknown): “(1) Knowledge: MMLU-Pro (Wang et al., 2024f), MMLU-Redux (Gema et al., 2024), GPQA (Rein et al., 2023), Su-perGPQA (Team, 2025), (2) Reasoning: AIME-25 (AIME, 2025), HMMT-25 (HMMT, 2025), LiveBench (2024-11-25) (White et al., 2024), (3) Code: LiveCodeBench v6 (Jain et al., 2024), CFEval, OJBench (Wa”
• A Survey of Model Architectures in Information Retrieval (2025, unknown): “The principle behind smoothing is that any text used to model a language captures only a limited subset of its linguistic patterns (or terms, in this case).”