Updated daily at 05:00 UTC
Benchmark
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
Leaderboard
Independent and third-party results only.
No independent or third-party results yet. Show all results