---
title: "Berkeley Function Calling Leaderboard: measurement, limitations and evaluation guide · Undominated.ai"
canonical: https://undominated.ai/benchmarks/bfcl/
description: "Tool-call correctness is more specific than general chat quality. Check the evaluation category and whether the model uses native function calling or a prompting workaround."
---

# Berkeley Function Calling Leaderboard: measurement, limitations and evaluation guide · Undominated.ai

> Tool-call correctness is more specific than general chat quality. Check the evaluation category and whether the model uses native function calling or a prompting workaround.

Evaluate structured tool use and agentic interactions

# Berkeley Function Calling Leaderboard

Tool-call correctness is more specific than general chat quality. Check the evaluation category and whether the model uses native function calling or a prompting workaround.

Source reviewed 2026-09-23 · [Official Berkeley Function Calling Leaderboard](https://gorilla.cs.berkeley.edu/leaderboard.html)

 On this page [What it measures](#measurement)[Limitations](#limits)[Fair comparison](#controls)[Your evaluation](#experiment)

## What it measures

BFCL evaluates function-calling accuracy and broader agentic interactions. Its public leaderboard distinguishes native function calling from prompted formats and describes overall accuracy as an unweighted average of its subcategories.

This is a method guide. Undominated does not publish or blend this benchmark’s scores into its model ranking.

## What the result does not establish

 - An aggregate does not show which particular tool-use failure affects your workflow.
- Native function calling and a prompted workaround may need different validation and retry logic.
- Benchmark cost and latency describe the published evaluation; they are not quotes for your application.

## Hold these conditions constant

 - Benchmark revision and evaluated category
- Native function calling or prompt format
- Tool schemas, multi-turn state and error handling
- Harness revision, inference settings and observed failures

## An evaluation for your team

Evaluate valid calls, missing arguments, irrelevant tools, failed tool responses and denied actions against your own schemas. Validate arguments before execution. Keep success, invalid-call rate, retries, cost and latency as separate observations.

Write down the task version, attempt count, accepted outcomes, observed spend and latency. Preserve failures in the denominator. A new model version or tool configuration deserves a new record.

 [Review tool permissions and transports →](/mcp-servers/)[Apply tool-use requirements →](/compare/)[Inspect workflow instructions →](/skills/)

Editorial guidance is not a new measurement. Follow the official source for its current benchmark definition and result history.

## Continue your investigation

 - [Inspect confidence intervals](/significance/)
- [Compare embedding evidence](/embeddings/)
- [Evaluate a shortlist](/compare/)
- [Read ranking rules](/methodology/)