Wikitopia
MMLU
conceptai_benchmark
Try in Playground →
Overview
Open source✓ Open Source
Use casemeasuring language model knowledge across 57 academic subjects from STEM to humanities
Also see
Alternative to
GPQA
Knowledge graph stats
Claims8
Avg confidence97%
Avg freshness99%
Last updatedUpdated 13h ago
Trust distribution
100% unverified
Governance
Not assessed
Contribute governance data →

MMLU

concept — also known as: Massive Multitask Language Understanding

Massive Multitask Language Understanding benchmark covering 57 academic subjects

Compare with...

used by

ValueTrustConfidenceFreshnessSources
Google○UnverifiedHighFresh1
OpenAI○UnverifiedHighFresh1

alternative to

ValueTrustConfidenceFreshnessSources
GPQA○UnverifiedHighFresh1

evaluates

ValueTrustConfidenceFreshnessSources
world knowledge and problem-solving ability○UnverifiedHighFresh1

open source

ValueTrustConfidenceFreshnessSources
true○UnverifiedHighFresh1

primary use case

ValueTrustConfidenceFreshnessSources
measuring language model knowledge across 57 academic subjects from STEM to humanities○UnverifiedHighFresh1

created by

ValueTrustConfidenceFreshnessSources
Dan Hendrycks et al.○UnverifiedHighFresh1

first released

ValueTrustConfidenceFreshnessSources
2020○UnverifiedHighFresh1

Alternatives & Similar Tools

GPQA
alternative to
Compare →

Related entities

Claim count: 8Last updated: 4/10/2026Edit history