CPC-Bench uses 7,102 NEJM clinicopathological cases to test medical diagnosis
GlassHealthHQ · x · 2026-07-21
CPC-Bench in one reply
CPC-Bench is a physician-validated benchmark built from 7,102 expert-curated New England Journal of Medicine Clinicopathological Conferences, spanning 1923–2025. It covers 4,009 unique diagnoses and 47,648 questions.
Its 10 tasks test differential diagnosis, testing plans, literature search, evolving-case diagnosis, medical Q&A, and the ability to weigh confirmatory vs. disconfirmatory evidence under limited information.
Related event: CPC-Bench Releases Validated Medical Benchmark(2 posts)→
More from Models
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11