Frontierscience (Prime Intellect)

Fresh

FrontierScience PhD-level science evaluation environment

Type: RL Env
Publisher: Prime Intellect
Tags: Science V1
Runtime: single-turn
License: unknown
Size: v0.1.0
Published: May 2026
Updated: Sep 2026
Canonical: app.primeintellect.ai/dashboard/environments/primeintellect/frontierscience

Cite

Notes

Only stored in your browser.

Attribution

README: api.primeintellect.ai/api/v1/environmentshub/primeintellect/frontierscience/@0.1.0/inspect

Attribution policy →

Evals this tool implements

Same problem set, this tool's harness. Run it to score a model on the test.

FrontierScience: Expert-Level Scientific Reasoning

OpenAI

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).

ActiveKnowledge