HealthAgentBench - EHR Event Modelling: leaderboard

Metric: Longitudinal EHR clinical event prediction adapted from EHRSHOT (6 tasks; success when test AUROC reaches the count plus gradient-boosting baseline): task success rate (%) over three attempts per task, a trial succeeding only when it meets the category success criterion; terminal environments in the Harbor framework, xhigh reasoning effort, web browsing disabled. Source: arxiv.org. Saturation forecast: Around December 2026. 10 models tracked.

Top models

#ModelScore
1Claude Opus 4.7 (xHigh)78
2GPT-5.5 (xHigh)72
3Claude Opus 4.8 (xHigh)67
4GPT-5.4 (xHigh)61
5GPT-5.3 Codex (xHigh)61
6GPT-5.4 Mini (xHigh)39

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