A benchmark for general AI assistants introduced by researchers from Meta, Hugging Face, and partner institutions. Its 466 real-world questions require reasoning, multimodal understanding, web browsing, and tool use.
Browse the latest scores, model modes, release dates, and parameter sizes for GAIA.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
No benchmark data available yet
