AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
OpenCompass Hub
CMMLU
CMMLU is a comprehensive Chinese evaluation benchmark specifically designed to assess the knowledge and reasoning abilities of language models in the context of the Chinese language. CMMLU covers 67 topics ranging from basic subjects to advanced professional levels. It includes tasks that require calculations and reasoning in natural sciences, as well as tasks involving knowledge from humanities, social sciences, and practical aspects like Chinese driving rules. Moreover, many tasks within CMMLU have answers specific to China, which might not be universally applicable in other regions or languages. As a result, CMMLU serves as a fully localized Chinese evaluation benchmark.
Evaluation context and evidence
- Source
- OpenCompass Hub
- Publisher
- Not recorded
- Benchmark release
- 2023-06-15
- Collected
- 2026-08-18
- Modality
- Not recorded
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 0
This source record has no numeric results in our collection. That does not mean a score of zero or that no public results exist. Consult the original resources above.