Background: Recent studies, including those by the National Board of Medical Examiners, have highlighted the remarkable capabilities of recent large language models (LLMs) such as ChatGPT in passing the United States Medical Licensing Examination (USMLE). However, there is a gap in detailed analysis of LLM performance in specific medical content areas, thus limiting an assessment of their potential utility in medical education. Objective: This study aimed to assess and compare the accuracy of successive ChatGPT versions (GPT-3.5, GPT-4, and GPT-4 Omni) in USMLE disciplines, clinical clerkships, and the clinical skills of diagnostics and management. Methods: This study used 750 clinical vignette-based multiple-choice questions to characterize the performance of successive ChatGPT versions (ChatGPT 3.5 [GPT-3.5], ChatGPT 4 [GPT-4], and ChatGPT 4 Omni [GPT-4o]) across USMLE disciplines, clinical clerkships, and in clinical skills (diagnostics and management). Accuracy was assessed using a standardized protocol, with statistical analyses conducted to compare the models’ performances. Results: GPT-4o achieved the highest accuracy across 750 multiple-choice questions at 90.4%, outperforming GPT-4 and GPT-3.5, which scored 81.1% and 60.0%, respectively. GPT-4o’s highest performances were in social sciences (95.5%), behavioral and neuroscience (94.2%), and pharmacology (93.2%). In clinical skills, GPT-4o’s diagnostic accuracy was 92.7% and management accuracy was 88.8%, significantly higher than its predecessors. Notably, both GPT-4o and GPT-4 significantly outperformed the medical student average accuracy of 59.3% (95% CI 58.3‐60.3). Conclusions: GPT-4o’s performance in USMLE disciplines, clinical clerkships, and clinical skills indicates substantial improvements over its predecessors, suggesting significant potential for the use of this technology as an educational aid for medical students. These findings underscore the need for careful consideration when integrating LLMs into medical education, emphasizing the importance of structured curricula to guide their appropriate use and the need for ongoing critical analyses to ensure their reliability and effectiveness.

Entrustable professional activities (EPAs) have been increasingly used as an assessment framework to formally capture the myriad ad hoc entrustment decisions that occur on a daily basis in clinical settings with learners present. Following the definition of Core EPAs for Entering Residency by the Association of American Medical Colleges in 2014, the American Board of Surgery (ABS) began to explore the utility of EPAs as a framework to support competency-based resident education within general surgery in 2016. As the complement of EPAs drafted for a specialty serve to define the core tasks of a professional within that discipline, initial efforts to define the entire scope of general surgery were fraught with difficulty as no commonly accepted definition of a general surgeon currently exists. Opting to prioritize a pilot of the EPA conceptual framework within surgical training rather than defining the entirety of the specialty, ABS leaders identified 5 EPAs that represent a core of general surgery with which to begin. This article details the process of choosing the initial set of EPAs and provides a roadmap for other disciplines interested in testing the feasibility of this assessment framework while garnering buy-in among the community of educators. Future steps, including implementation of the existing 5 EPAs beyond the initial pilot sites and drafting and implementation of the additional complement of EPAs, are also described.