EHRBench - MIMIC-IV: leaderboard
EHRBench (2026) tests LLMs on clinical decision questions generated from real patient records and verified against biomedical knowledge bases, posed as multiple-choice questions with 4 to 6 options. This board is accuracy in percent on the questions built from MIMIC-IV records; higher is better.
Metric: Accuracy (%) on the questions built from MIMIC-IV records, EHR-grounded multiple-choice clinical decision questions (4, 5 and 6 options) built from MIMIC-III, MIMIC-IV and PROMOTE encounter trajectories with knowledge-base verification, JSON-constrained answers, deterministic decoding; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 31 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 Instant | 71.06 | #309 |
| 2 | GPT-4.1 | 69.77 | #506 |
| 3 | GPT-5 Chat | 69.18 | #452 |
| 4 | Llama 3.3 70B Instruct | 67.94 | #1394 |
| 5 | GPT-4.1 Mini | 67.36 | #799 |
| 6 | Qwen 3 32B | 67.18 | #983 |
| 7 | Qwen 2.5 32B | 67 | #1347 |
| 8 | GLM-4 32B (0414) | 66.45 | #1525 |
| 9 | GPT-5 Mini | 66.05 | #373 |
| 10 | m1-32B-1k | 65.49 | #1247 |
| 11 | Mistral Small 3 | 65.36 | #1809 |
| 12 | EHRBench llama3-70B (checkpoint unspecified) | 63.72 | |
| 13 | doctor-r1-8B | 62.26 | #1634 |
| 14 | Qwen 3 8B | 62.11 | #1890 |
| 15 | GPT-4.1 Nano | 61.89 | #2065 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=ehrbench-mimic-iv · How It Works · Data refreshed daily, snapshot 2026-11-22.