Tool use · benchmark

Berkeley Function Calling

Check single-turn, multi-turn and agentic function calls.

What it measures

BFCL V4 overall accuracy (%)

Native function calling and prompted calls are separately declared.

Public evaluation code. Check upstream code and dataset terms.

Open source / dataset · Run instructions · Official results

Reported ranking tracks

• BFCL V4 · overall · 109 entries · captured 2026-10-07T07:01:28Z

Explore all evaluations · Find a competition