C-Eval

C-Eval is a multi-level and multi-disciplinary Chinese evaluation suite designed for large language models. It was jointly launched by researchers from Shanghai Jiao Tong University, Tsinghua University, Hong Kong University, and the University of Edinburgh in May 2023. It contains 13,948 multiple-choice questions, covering 52 different disciplines and four difficulty levels, aiming to evaluate the Chinese comprehension ability of large models.