OpenAI

FrontierScience: Expert-Level Scientific Reasoning

Evaluates AI capabilities for expert-level scientific reasoning across physics, chemistry, and biology. Contains 160 problems with two evaluation formats: Olympic (100 samples with reference answers) and Research (60 samples with rubrics).

scientific-reasoningbiology-subsettext
Status
cataloged
Saturation
unsaturated
Runnable
yes
Cost to run
high

Editor's note

Expert / olympiad-level reasoning across physics, chemistry, and biology (160 problems). Only the biology subset is in-scope for us; unsaturated and hard. Already in inspect_evals.

Results

Verified scores pending — this eval is cataloged; our own inspect_ai reproduction is the next step.

Reproduce: inspect_evals implementation

Sources