RealICU (Local Window) - Patient Status: leaderboard
RealICU (Shen et al., 2026) replays MIMIC-IV intensive-care stays in 30-minute windows and scores an LLM against hindsight labels from senior ICU physicians on the 930 windows of RealICU-Gold. Patient Status: accuracy (0-1) of the patient-status assessment at each window, higher is better. Local-window protocol: the model sees only the current window.
Metric: Accuracy (0-1; patient-status class per 30-minute window against hindsight physician labels, 930 RealICU-Gold windows; local-window strategy, only the current window in the prompt). Source: arxiv.org. Saturation forecast: Around November 2027. 3 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 0.32 | #91 |
| 2 | GPT-5.4 | 0.23 | #121 |
| 3 | Qwen 3 235B A22B | 0.15 | #622 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=realicu-local-window-patient-status · How It Works · Data refreshed daily, snapshot 2026-11-12.