Unverified50% confidenceFactExact time
MMLU was proposed in 2020 by Dan Hendrycks and others at the University of California, Berkeley, covering 57 subject areas and approximately 15,000 multiple-choice questions.
1
Sources
50%
Confidence
Long-term
Relevance
9/4/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedMMLU contains approximately 15,000 multiple-choice questions across 57 subjects, covering knowledge from high school to graduate level75% similarUnverifiedMMLU covers 57 subjects and nearly 16,000 multiple-choice questions; HumanEval was developed by OpenAI and contains 164 programming problems; GSM8K contains 8,500 elementary school math word problems.69% similarPartially VerifiedMMLU (Massive Multitask Language Understanding) covers multiple-choice questions across 57 subjects, testing the breadth and depth of a model's knowledge from humanities and social sciences to STEM.64% similarUnverifiedThe MATH dataset was proposed by Hendrycks et al. in 2021 and contains 12,500 competition-level mathematics problems spanning seven sub-domains63% similarUnverifiedML理论知识通常以斯坦福CS229、Andrew Ng的Machine Learning专项课程为参考体系56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/853399API
curl https://kongchang.com/api/v1/knowledge/claims/853399MCP
get_claim(id=853399)