CMMLU
Multilingual
text
+
+
+
+
About
CMMLU (Chinese Massive Multitask Language Understanding) is a comprehensive benchmark designed to evaluate AI models' performance on Chinese language tasks across multiple domains. Covering reading comprehension, text classification, knowledge reasoning, and specialized subjects, it provides extensive assessment of Chinese language capabilities. CMMLU addresses the significant gap in evaluating Chinese-specific language understanding and cultural knowledge in large language models.
+
+
+
+
Evaluation Stats
Total Models1
Organizations1
Verified Results0
Self-Reported1
+
+
+
+
Benchmark Details
Max Score1
Language
en
+
+
+
+
Performance Overview
Score distribution and top performers
Score Distribution
1 models
Top Score
90.1%
Average Score
90.1%
High Performers (80%+)
1Top Organizations
#1Alibaba Cloud / Qwen Team
1 model
90.1%
+
+
+
+
Leaderboard
1 models ranked by performance on CMMLU
| License | Links | ||||
|---|---|---|---|---|---|
| Jul 23, 2024 | tongyi-qianwen | 90.1% |
