Verified80% confidenceFactExact time
MMLU (Massive Multitask Language Understanding) contains multiple-choice questions across 57 subjects and is used to test the breadth of a model's knowledge.
4
Sources
80%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMMMU (Massive Multidiscipline Multimodal Understanding) requires models to answer questions that demand joint image-text reasoning across 30 disciplines including medicine, law, and the arts.75% similarUnverifiedMMLU, GSM8K, HumanEval and C-Eval are common large-model benchmark suites, focusing respectively on multidisciplinary knowledge, elementary-school math reasoning, code generation and comprehensive Chinese ability.72% similarUnverifiedMMLU的生物医学部分主要来源于教材和标准化考试题库，主要考察概念性知识记忆而非数据分析推理能力71% similarUnverifiedMMLU was once the gold standard for measuring the knowledge level of large language models, and was an almost mandatory metric in every model release report in the era when ChatGPT first appeared.70% similarUnverifiedDecision Index is a benchmark leaderboard specifically targeting decision-making tasks, and its evaluation metrics differ from those of general language model leaderboards such as MMLU and HellaSwag.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/895389API
curl https://kongchang.com/api/v1/knowledge/claims/895389MCP
get_claim(id=895389)