Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks
Published in NeurIPS 2026 (Evaluations & Datasets Track) · ICML 2026 FM4LS Workshop (Poster), 2026
Medmarks was cited, alongside Stanford’s MedHELM, as a third-party evaluation in OpenAI’s announcement Making ChatGPT better for clinicians (April 2026).