Benchmark

FrontierScience

Measures: Expert-written physics, chemistry and biology problems in two tracks: Olympiad (short answers, IPhO/IChO/IBO level) and Research (PhD-level sub-problems graded on a 10-point rubric, counted correct at 7+ points); scored as accuracy per track.

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

Paper

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

No results to show.