Medical Chat is an AI platform to assist healthcare professionals in their daily diagnostic work by providing reliable and accurate medical information. As far as we know, it is the most accurate medical question-answering system available for public use.
Chat Data
π― Accuracy Performance test: We have achieved 98.1% (637/649) on the USMLE sample test. As far as our knowledge extends, this represents the highest level of performance among question-answering systems evaluated on the USMLE sample exam. We also have achieved 97.8% (1245/1273) accuracy on the MedQA sample test. This outcome places Medical Chat in first position on the Official Leaderboard, surpassing Google's Med-PaLM 2 and Google's Flan-PaLM (67.6%). You can review this detailed report for the full evaluation process. The evaluation procedure is also open sourced in this GitHub repository. Anyone can reproduce the evaluation procedure following the GitHub repo instructions.