Voxel51/MedXpertQA
收藏Hugging Face2025-05-22 更新2025-07-05 收录
下载链接:
https://hf-mirror.com/datasets/Voxel51/MedXpertQA
下载链接
链接失效反馈官方服务:
资源简介:
MedXpertQA是一个具有挑战性和综合性的医学多项选择基准,旨在评估AI模型在医学知识和高级推理能力方面的专家级能力。它包括4,460个问题,涵盖17个医学专业和11个身体系统,分为两个主要子集:MedXpertQA Text用于文本评估和MedXpertQA MM用于多模态评估。该数据集以其对专业医学场景的全面覆盖、专家级难度以及与现实临床决策过程的紧密契合而脱颖而出。
MedXpertQA is a highly challenging and comprehensive medical multiple-choice benchmark designed to evaluate expert-level medical knowledge and advanced reasoning capabilities in AI models. It consists of 4,460 questions spanning 17 medical specialties and 11 body systems, with two main subsets: MedXpertQA Text for text-only evaluations and MedXpertQA MM for multimodal assessments. The dataset stands out for its comprehensive coverage of specialized medical scenarios, expert-level difficulty, and alignment with realistic clinical decision-making processes.
提供机构:
Voxel51



