MedCase-Structured (1-Shot): leaderboard
Metric: Diagnostic accuracy (%; the model reads a case as a terminology-coded FHIR R4 bundle with the final diagnosis hidden and names the most likely diagnosis; an LLM judge (Claude Sonnet 4.6) decides clinical equivalence to the reference; mean of three runs; one example from the training split in the prompt; medium reasoning, temperature 1.0, 800 generated tokens). Source: arxiv.org. Saturation forecast: Around April 2027. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 (Medium) | 56.82 |
| 2 | GPT-5.4 (Medium) | 55.45 |
| 3 | Gemini 3.1 Pro (Preview) (Medium) | 45.45 |
Interactive version: theaggregate.ai/benchmark?slug=medcase-structured-1-shot · How It Works · Data refreshed daily, snapshot 2026-09-26.