
Academic lab · Berkeley, United States
GorillaUC Berkeley
A UC Berkeley project that built Gorilla LLM and the Berkeley Function-Calling Leaderboard for evaluating tool and API use by language models.
Berkeley, United States
- Founded
- 2023
- Type
- Academic lab
- Based in
- Berkeley, United States
- Key papers
- 3
- Featured projects
- 4
About
Gorilla is a UC Berkeley research project led by Shishir G. Patil, Tianjun Zhang, Xin Wang and Joseph E. Gonzalez. It produced Gorilla LLM, an open-source model that invokes API calls, and a paper posted as arXiv 2305.15334.
Related releases include OpenFunctions v2, a 6.91B-parameter function-calling model, RAFT for retrieval-aware fine-tuning, GoEX, a runtime for executing LLM-generated actions with undo and damage confinement, and the Berkeley Function-Calling Leaderboard, which covers about 2,000 question-function-answer pairs across Python, Java, JavaScript and REST.
Mission and ambitionsGorilla aims to let language models use tools and APIs reliably, and to give the community open models and benchmarks for measuring that ability.
Known for
- 01
Gorilla LLM for API calls
- 02
Berkeley Function-Calling Leaderboard
- 03
RAFT fine-tuning method
- 04
GoEX execution engine
Milestones
- 2023
Gorilla paper
Introduced an LLM connected to large API collections.
- 2024
RAFT
Retrieval-aware fine-tuning method.
- 2024
GoEX
Runtime for LLM-generated actions.
Open source
Training and evaluating LLMs for function calls
BFCL dataset
- APIBenchdataset
API benchmark
OpenFunctions v2
Research papers
Notable releases
Openness
Apache-2.0 code, models and datasets.
People
- Shishir G. PatilLead researcher
- Tianjun ZhangResearcher
- Xin WangResearcher
- Joseph E. GonzalezProfessor, UC Berkeley
Listed from the lab's own pages and public profiles.
Contact and community
Via website.
Community Discord linked from the website.
Sources
Compiled from the lab's public pages, Hugging Face and GitHub. Last checked 2026-11-17. Something wrong or out of date? Tell us on Discord.



