Unverified50% confidenceBenchmarkExact time

MMLU覆盖57个学科领域，题目来源于律师资格、医学执照、GRE等真实人类专业考试，用于评估通用知识理解能力

1

Sources

50%

Confidence

Long-term

Relevance

7/18/2026

First Seen

Sources

Exposing the GPT-5.6 Marketing Scam: Are the Sol/Terra/Luna Sub-Models Real Releases or Just a Trap?

Related Claims

UnverifiedMMLU covers multiple-choice questions across 57 subject areas, while GPQA focuses on questions requiring doctoral-level expertise.85% similar VerifiedMMLU covers a breadth-of-general-knowledge test spanning 57 subjects.84% similar UnverifiedMMLU基准测试涵盖数学、历史、法律、医学等57个学科领域80% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/550155

API

curl https://kongchang.com/api/v1/knowledge/claims/550155

MCP

get_claim(id=550155)