AI Model Evaluation

CMMLU

CMMLU is a comprehensive Chinese language assessment benchmark specifically designed to evaluate the knowledge and reasoning ability of language models in Chinese cont...

Tags:

CMMLU is a comprehensive Chinese language assessment benchmark specifically designed to evaluate the knowledge and reasoning ability of language models in Chinese contexts, covering 67 topics from basic disciplines to advanced professional levels. It includes natural sciences that require computation and reasoning, humanities and social sciences that require knowledge, and Chinese driving rules that require common sense of life. In addition, many tasks in CMMLU have Chinese specific answers and may not be universally applicable in other regions or languages. Therefore, it is a completely Chinese language testing benchmark.

data statistics

Relevant Navigation

No comments

No comments...