Unverified90% confidenceFactExact time
MMLU was introduced in 2021 by UC Berkeley and other institutions as a large-scale multitask language understanding benchmark
1
Sources
90%
Confidence
Long-term
Relevance
8/3/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedMMLU由加州大学伯克利分校于2020年发布，包含来自57个学科的约15,000道多项选择题76% similarUnverifiedMMLU于2021年由Hendrycks等人提出，题目来源于真实人类专业考试，覆盖57个学科领域64% similarVerified「基础模型」这一术语由斯坦福大学HAI研究院于2021年正式提出64% similarUnverifiedMMLU于2021年由Dan Hendrycks等人发布，涵盖57个学科共14,000余道题目64% similarUnverifiedvLLM由UC伯克利于2023年开源，凭借PagedAttention技术将LLM推理吞吐量提升2-4倍64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/680089API
curl https://kongchang.com/api/v1/knowledge/claims/680089MCP
get_claim(id=680089)