Who is the Berkeley Function-Calling Leaderboard designed for?

It is aimed at researchers, framework authors, and engineering teams who need rigorous, defensible numbers to pick a model for an agent stack, rather than relying on vendor marketing.

How can I reproduce the benchmark results locally?

The benchmark, dataset, and harness are open source on GitHub and can be installed via the `bfcl-eval` PyPI package, allowing you to run evaluations locally rather than trusting the dashboard alone.

What specific aspects of function calling does the benchmark evaluate?

It scores native function-calling and prompt-based approaches across multi-turn dialogue, web-search-augmented calls, and format sensitivity, while also tracking cost and latency alongside correctness.

Is the Berkeley Function-Calling Leaderboard a paid product?

No, it is free and open source. The only cost incurred is for the inference required when reproducing runs, particularly on frontier APIs.

Does the benchmark include interactive tools for testing?

Yes, the site ships a live demo for testing function-calling behavior with custom prompts and tool schemas, along with a 'Wagon Wheel' radar chart for side-by-side model comparison.

Berkeley Function-Calling Leaderboard

✓ Editorially verified

Open benchmark from UC Berkeley that ranks LLMs on real-world tool-use and function-calling accuracy.

Free· Free and open source; you pay only for inference when reproducing runs.EvaluationMulti-model8.1 / 10

Visit website →

In short

The Berkeley Function-Calling Leaderboard is a free, open-source benchmark that measures LLM performance on real-world tool use and function calling. It is best for engineering teams needing rigorous, reproducible data to select models for agent applications, tracking accuracy, cost, and latency across multi-turn scenarios.

Best for

Pick BFCL if you're choosing an LLM for an agent or tool-using app and need defensible numbers on function-calling quality.

Skip if

Skip it if you want a general chatbot leaderboard or a turnkey eval SaaS with dashboards and team features.

The Berkeley Function-Calling Leaderboard (BFCL) is a public evaluation benchmark from UC Berkeley's Gorilla research group that measures how well large language models execute function calls and use tools. Now on version 4, it scores native function-calling and prompt-based approaches across multi-turn dialogue, web-search-augmented calls, format sensitivity, and overall unweighted accuracy across sub-categories, with cost and latency tracked alongside correctness.

It's aimed at researchers, framework authors, and engineering teams who are picking a model for an agent stack and need a more rigorous answer than vendor marketing. The benchmark, dataset, and harness are open source on GitHub and pinnable via the `bfcl-eval` PyPI package, so you can reproduce numbers locally rather than trust the dashboard alone. The leaderboard itself is free; the only cost is the inference you spend re-running it. Work behind BFCL was presented at ICML 2025.

The site also ships a live demo for poking at function-calling behavior with custom prompts and tool schemas, a 'Wagon Wheel' radar chart for side-by-side model comparison, and a Discord for community contributions and new task submissions. It is not a product you buy; it's reference infrastructure for the agent-tooling ecosystem.

Editor's take

BFCL is one of the few function-calling benchmarks serious agent teams actually cite, and the fact that the harness is pip-installable means you can verify the numbers instead of squinting at a webpage. Treat it as a strong prior, then re-run on your own tool schemas before committing a model.

— The AI Tool Bible editorial team

Pros

✅ Reproducible: open dataset, harness, and pip-installable eval package
✅ Covers multi-turn, web search, format sensitivity, not just single-shot calls
✅ Tracks cost and latency alongside accuracy
✅ Backed by peer-reviewed work (ICML 2025) and actively updated
✅ Interactive demo lets you sanity-check models on your own schemas

Cons

⚠️ Academic benchmark, not a managed product or SLA
⚠️ Function-calling focus only; not a general LLM leaderboard
⚠️ Reproducing top runs can get expensive on frontier APIs

Use cases

function-calling evaltool-use benchmarkingagent model selectionmulti-turn evalcost/latency comparison

Frequently asked

Who is the Berkeley Function-Calling Leaderboard designed for?: It is aimed at researchers, framework authors, and engineering teams who need rigorous, defensible numbers to pick a model for an agent stack, rather than relying on vendor marketing.
How can I reproduce the benchmark results locally?: The benchmark, dataset, and harness are open source on GitHub and can be installed via the `bfcl-eval` PyPI package, allowing you to run evaluations locally rather than trusting the dashboard alone.
What specific aspects of function calling does the benchmark evaluate?: It scores native function-calling and prompt-based approaches across multi-turn dialogue, web-search-augmented calls, and format sensitivity, while also tracking cost and latency alongside correctness.
Is the Berkeley Function-Calling Leaderboard a paid product?: No, it is free and open source. The only cost incurred is for the inference required when reproducing runs, particularly on frontier APIs.
Does the benchmark include interactive tools for testing?: Yes, the site ships a live demo for testing function-calling behavior with custom prompts and tool schemas, along with a 'Wagon Wheel' radar chart for side-by-side model comparison.