BrowseComp

Measures: An agent with web search and browsing must find hard-to-locate, multi-constraint facts across many websites and return a short answer; scored as % of 1,266 questions answered correctly against the reference.

Maintainer: OpenAI
Introduced: 2025
Status: Active
Saturation: Saturated
Typical provenance: Self-reported
In scoring set: No

Paper

Leaderboard

Show independent results only

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

No results to show.