chinese-llm-benchmark
Active·★ 6.5k·Updated 2026-09-30
★ Trending★ Essential
ReLE Benchmark (formerly CLiB) provides a continuously updated evaluation for Chinese AI large language models, covering over 337 commercial and open-source LLMs. It offers multi-dimensional capability assessments across various domains, along with comprehensive rankings and a large defect library for model improvement.
#LLM Evaluation#Chinese LLMs#AI Benchmark#Model Ranking#Defect Analysis#Data Analysis#Communication
01
Features
01Extensive coverage of 337+ commercial and open-source Chinese LLMs.
02Multi-dimensional evaluation across 7 main domains and ~300 sub-dimensions.
03Provides detailed ranking lists for various capabilities and specific domains.
04Offers a large defect library with over 2 million LLM flaws for research and improvement.
05Supports customized model selection and free evaluation services for private models.
02
Compatibility
OpenAI (GPT series)
Supported
Verified via docs
Google (Gemini series)
Supported
Verified via docs
Anthropic (Claude series)
Supported
Verified via docs
Baidu (ERNIE series)
Supported
Verified via docs
Alibaba (Qwen series)
Supported
Verified via docs
DeepSeek
Supported
Verified via docs
03
Use cases
↳Comparing and selecting the best performing LLMs for specific applications.
↳Identifying weaknesses and improving the capabilities of large language models.
↳Benchmarking private or custom LLMs against public models for performance and cost optimization.
04
Alternatives
Comments
Log in to leave a comment
No comments yet. Be the first!