Wikitopia
GPQA
conceptai_benchmark
Try in Playground →RSS
Overview
Open source✓ Open Source
Use caseevaluating expert-level scientific reasoning with questions that are Google-proof
Also see
Alternative to
MMLU
Knowledge graph stats
Claims6
Avg confidence97%
Avg freshness99%
Last updatedUpdated yesterday
Trust distribution
100% unverified
Governance
Not assessed
Contribute governance data →

GPQA

concept — also known as: GPQA Diamond

Graduate-Level Google-Proof Q&A benchmark with expert-level science questions

Compare with...

alternative to

ValueTrustConfidenceFreshnessSources
MMLU○UnverifiedHighFresh1

evaluates

ValueTrustConfidenceFreshnessSources
graduate-level reasoning in biology, physics, and chemistry○UnverifiedHighFresh1

open source

ValueTrustConfidenceFreshnessSources
true○UnverifiedHighFresh1

primary use case

ValueTrustConfidenceFreshnessSources
evaluating expert-level scientific reasoning with questions that are Google-proof○UnverifiedHighFresh1

first released

ValueTrustConfidenceFreshnessSources
2023○UnverifiedHighFresh1

created by

ValueTrustConfidenceFreshnessSources
David Rein et al.○UnverifiedHighFresh1

Alternatives & Similar Tools

MMLU
alternative to
Compare →

Related entities

Claim count: 6Last updated: 4/9/2026Edit history