C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models

• Main Authors: Huang, Yuzhen, Bai, Yuzhuo, Zhu, Zhihao, Zhang, Junlei, Zhang, Jinghan, Su, Tangjun, Liu, Junteng, Lv, Chuancheng, Zhang, Yikai, Lei, Jiayi, Fu, Yao, Sun, Maosong, He, Junxian
• Format: Journal Article
• Language: English
• Published: 14.05.2023
• Subjects: Computer Science - Computation and Language
• DOI: 10.48550/arxiv.2305.08322

New NLP benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present C-Eval, the first comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context. C-Eval comprises multiple-choice questions across four difficulty levels: middle school, high school, college, and professional. The questions span 52 diverse disciplines, ranging from humanities to science and engineering. C-Eval is accompanied by C-Eval Hard, a subset of very challenging subjects in C-Eval that requires advanced reasoning abilities to solve. We conduct a comprehensive evaluation of the most advanced LLMs on C-Eval, including both English- and Chinese-oriented models. Results indicate that only GPT-4 could achieve an average accuracy of over 60%, suggesting that there is still significant room for improvement for current LLMs. We anticipate C-Eval will help analyze important strengths and shortcomings of foundation models, and foster their development and growth for Chinese users.