Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
Med42huggingface.co · Low evidenceMed42 is an open access clinical large language model developed by M42 Health, built on LLaMA 2 with 70 billion parameters to provide high-quality answers to medical questions. It achieves competitive performance on medical benchmarks, including 72% accuracy on the US Medical Licensing Examination sample exam, surpassing prior state-of-the-art among openly available medical LLMs.
Parse Score
Sources
arxiv.org shapes more of what AI says about Med42 than any other source, at 100% of its citations.