mariocedo/GlobalMedQA

GlobalMedQA是一个标准化的多语言医疗多项选择题数据集，旨在评估大型语言模型在医疗领域的知识。该数据集整合了来自14个国家、13种语言的考试问题，并按照欧洲医学专家联盟（UEMS）的分类体系进行了统一格式化和分类。它支持单选和多项选择题，并包含语言、国家、年份和来源等元数据。GlobalMedQA使得可以在应用医学推理和问题回答方面对LLM进行跨语言的性能比较。

GlobalMedQA is a standardized multilingual medical multiple-choice question dataset designed to benchmark large language models in the healthcare domain. The dataset integrates exam questions from 14 countries and 13 languages, standardized into a unified schema with consistent metadata and specialty classification based on the European Union of Medical Specialists (UEMS) taxonomy. It supports both single-answer and multiple-answer questions and includes metadata on language, country, year, and source. GlobalMedQA enables cross-lingual performance comparison of LLMs in applied medical reasoning and question answering.