New Natural Langauge Process~(NLP) benchmarks are urgently needed to align with the rapid development of large language models (LLMs). We present Xiezhi, the most comprehensive evaluation suite designed to assess holistic domain knowledge. Xiezhi comprises multiple-choice questions across 516 diverse disciplines ranging from 13 different subjects with 220,000 questions and accompanied by Xiezhi-Specialty and Xiezhi-Interdiscipline, both with 15k questions. We conduct evaluation of the 47 cutting-edge LLMs on Xiezhi. Results indicate that LLMs exceed average performance of humans in science, engineering, agronomy, medicine, and art, but fall short in economics, jurisprudence, pedagogy, literature, history, and management. We anticipate Xiezhi will help analyze important strengths and shortcomings of LLMs, and the benchmark is released in https://github.com/MikeGu721/XiezhiBenchmark .

翻译：新的自然语言处理（NLP）基准迫切需与大型语言模型（LLMs）的快速发展保持一致。我们提出Xiezhi，这是目前最全面的评估套件，旨在评估全领域知识。Xiezhi包含跨越13个不同学科、516个多样化领域的22万道选择题，并附带Xiezhi-Specialty和Xiezhi-Interdiscipline两个各含1.5万道题的子集。我们在Xiezhi上对47个先进的LLMs进行了评估。结果表明，LLMs在科学、工程、农学、医学和艺术领域超越了人类平均表现，但在经济学、法学、教育学、文学、历史和管理学领域仍存在不足。我们期待Xiezhi将有助于分析LLMs的重要优势与缺陷，该基准已发布于https://github.com/MikeGu721/XiezhiBenchmark。