The chat records of diagnoses for China's first batch of rare disease catalog by ChatGPT-4o and the four LLMs

This study aimed to evaluate the diagnostic accuracy of ChatGPT-4o and 4 open-source LLMs (qwen2.5:7b, Llama3.1:8b, qwen2.5:72b, and Llama3.1:70b) for rare diseases, assesses the language effect on diagnostic performance, and explore retrieval augmented generation (RAG) and chain-of-thought (CoT) reasoning. This supplementary material includes the first rare disease catalog of ChatGPT-4o in China and all diagnostic chat records for four LLMs in this study. This file contains a collection of 11 chat content. The LLM diagnostic order of cases can be found in Appendix 2 of Multimedia.