Knowledge-based assessments remain a foundation of medical education. However, leveraging these resources for learning requires detailed and verifiable feedback. To this aim, OpenEvidence has developed a new AI system that not only accurately answers each question, but also teaches the reasoning behind each answer, providing accurate references using gold-standard sources of medical knowledge such as the New England Journal of Medicine (NEJM) and the Journal of the American Medical Association (JAMA). OpenEvidence, a medical search platform that currently provides evidence-based clinical decision and practice support for over 40% of physicians in the United States, was the first to develop an AI system to score over 90% on the USMLE. OpenEvidence now becomes the first AI in history to score a perfect 100% on the United States Medical Licensing Examination (USMLE).
Medical education is costly with many inequalities in access to quality tools and educational resources. OpenEvidence will be releasing a number of tools throughout this academic year to democratize access to quality medical education resources and support continued learning throughout training and clinical practice. These tools are built with a focus on education, creating vignette and case based learning customizable by training level with reasoning and explanations grounded in the current medical literature.
This 100% USMLE achievement is the result of a six-month effort to improve the core technologies that power OpenEvidence, and demonstrates OpenEvidence’s commitment and continued effort to improve physician knowledge at all levels of medical education.
A question-by-question explanation of the correct answer to every single question on an official United States Medical Licensing Examination (USMLE) is attached.
We do not run on questions that contain images. We make two modifications to the data provided by Kung et al., 2023. First, we use the spreadsheets provided by Kung et al., 2023, but fix a recording error with Question #78 from the Step 3 spreadsheet.
Additionally, we found that one question, question 125 from the Step 3 exam, gives an incorrect answer. This question was reviewed by seven independent psychiatrists, who agreed with the OpenEvidence answer. This conclusion is also supported by the Wellbutrin’s FDA label, which the reasoning in OpenEvidence’s answer references. The FDA label specifically addresses the concern within this question and contradicts the provided answer.[2]
The USMLE is a three-step examination for medical licensure in the United States. It assesses one’s ability to apply knowledge, concepts, and principles, as well as demonstrate fundamental patient-centered skills that form the foundation of safe and effective patient care. Traditionally, the USMLE has been a rigorous examination that demands a broad understanding of biomedical and clinical sciences, testing not only factual recall, but also decision-making ability.
OpenEvidence is the fastest-growing clinical decision support platform in the United States, and the most widely used medical search engine among U.S. clinicians. Trusted by hundreds of thousands of verified physicians, nurses, and other healthcare professionals, OpenEvidence is actively used across more than 10,000 hospitals and medical centers nationwide and by over 40% of physicians in the United States who log in daily to make high-stakes clinical decisions at the point of care.
OpenEvidence continues to grow by over 75,000 new verified U.S. clinician registrations each month. Aside from Google itself, there has never been a piece of technology adopted by clinicians as quickly as OpenEvidence. OpenEvidence is transforming how frontline healthcare providers access, evaluate, and apply the world’s medical knowledge. More than 100 million Americans this year will be treated by a doctor who used OpenEvidence.
OpenEvidence was founded by Daniel Nadler and Zachary Ziegler. Founded with the mission to organize and expand global medical knowledge, OpenEvidence is redefining evidence-based medicine in real-time. In recognition of this impact, in 2025, OpenEvidence founder Daniel Nadler, PhD, was named to the TIME100 Health list of the 100 Most Influential People in global health.
CONTACT: contact@openevidence.com