Benchmark

CMMLU

CMMLU (Chinese Massive Multitask Language Understanding) is a comprehensive Chinese benchmark that evaluates the knowledge and reasoning capabilities of…

Modality
text
Categories
reasoning, language, general
Openness
unknown
Source
llm_stats
Reported scores
6

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
ERNIE 4.5Baidu0.3982025-06-25evidence
LongCat-Flash-ChatMeituan0.84342025-08-29evidence
LongCat-Flash-LiteMeituan0.82482026-02-05evidence
MiMo-V2.5-ProXiaomi0.9022026-04-27evidence
MiniCPM-SALAOpenBMB0.81552026-02-11evidence
Qwen2 72B InstructQwen0.9012024-07-23evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.