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
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 (xHigh) | 78 |
| 2 | GPT-5.5 (xHigh) | 72 |
| 3 | Claude Opus 4.8 (xHigh) | 67 |
| 4 | GPT-5.4 (xHigh) | 61 |
| 5 | GPT-5.3 Codex (xHigh) | 61 |
| 6 | GPT-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.