EarlyDx: leaderboard

Metric: Primary-track F1 (%): micro-averaged F1 of the predicted free-text diagnoses against the evidence-supported ED-encounter diagnoses (matched by a semantic judge), 6,975 test encounters with evidence clipped at hospital admission; zero-shot prompting; higher is better. Source: arxiv.org. Saturation forecast: Around August 2028. 7 models tracked.

Top models

#ModelScore
1GPT-5.540
2GLM-5.237
3MedGemma-4B32
4Claude Opus 4.828
5Nemotron 3 Ultra25

Interactive version: theaggregate.ai/benchmark?slug=earlydx · How It Works · Data refreshed daily, snapshot 2026-09-29.