CMMLU
CMMLU (Chinese Massive Multitask Language Understanding) is a comprehensive Chinese benchmark that evaluates the knowledge and reasoning capabilities of large language models across 67 different subject topics. The benchmark covers natural sciences, social sciences, engineering, and humanities with multiple-choice questions ranging from basic to advanced professional levels.
Qwen2 72B Instruct from Alibaba Cloud / Qwen Team currently leads the CMMLU leaderboard with a score of 0.901 across 5 evaluated AI models.
Qwen2 72B Instruct leads with 90.1%, followed by 
LongCat-Flash-Chat at 84.3% and LongCat-Flash-Lite at 82.5%.
Progress Over Time
Interactive timeline showing model performance evolution on CMMLU
CMMLU Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 |  Alibaba Cloud / Qwen Team | 72B | — | — | ||
| 2 | Meituan | 560B | 128K | $0.30 / $1.20 | ||
| 3 | Meituan | 69B | 256K | $0.10 / $0.40 | ||
| 4 |  OpenBMB | 9B | — | — | ||
| 5 |  Baidu | 21B | — | — |
FAQ
Common questions about CMMLU.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions