Accessibility settings

Published on in Vol 28 (2026)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/96885, first published .
Laptop displaying medical icons: clipboard, heart, stethoscope, brain, pills.

Medical Reasoning in Large Language Models: Development and Evaluation of the MedEvalArena Benchmark

Medical Reasoning in Large Language Models: Development and Evaluation of the MedEvalArena Benchmark

Preethi Prem   1 , BS ;   Vikasini Kuppa   2 ;   Kie Shidara   3 , BS ;   Esmé Wheeler   3 , BA ;   Gene Chang   4 ;   Feng Liu   5 , PhD ;   Ahmed Alaa   4 , PhD ;   Danilo Bernardo   3 , MD

1 Carle Illinois College of Medicine, University of Illinois Urbana-Champaign, Champaign, IL, United States

2 College of Natural and Agricultural Sciences, University of California, Riverside, Riverside, CA, United States

3 Weill Institute of Neurology and Neurosciences, University of California, San Francisco, San Francisco, CA, United States

4 Department of Neurosciences, University of California, Berkeley, Berkeley, CA, United States

5 Department of Industrial & Systems Engineering, Rutgers University, Piscataway, NJ, United States

Corresponding Author:

  • Danilo Bernardo, MD
  • Weill Institute of Neurology and Neurosciences, University of California, San Francisco
  • 1825 Fourth Street, Suite 5A
  • San Francisco, CA 94143
  • United States
  • Phone: 1 415-353-2437
  • Email: dbernardoj@gmail.com