MR-Bench - Medication Imputation: leaderboard
MR-Bench (2026) tests decision-oriented clinical reasoning on 1,000 MIMIC-IV hospital admissions with eight-option questions, at temperature 0.5. This board asks for the masked medication of a partly shown prescription list, among distractors that include interacting or contraindicated drugs. Accuracy in percent; higher is better.
Metric: Accuracy (%, times 100) at picking the masked medication among distractors that include interacting or contraindicated drugs; 1,000 MIMIC-IV hospital admissions, eight-option questions, temperature 0.5, an answer counted from the first or the last option letter the output names, whichever scores higher over the dataset; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 24 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3 Pro | 55 | #145 | |
| 2 | GPT-5 | 54.4 | #178 | |
| 3 | DeepSeek V3.2 | Thinking | 48.4 | #419 |
| 4 | Qwen 3 Max | 44.6 | #415 | |
| 5 | GPT-4o | 36.3 | #751 | |
| 6 | MedS3-8B | 28.7 | ||
| 7 | Qwen 3 4B 2507 (Thinking) | 27.2 | #1433 | |
| 8 | Qwen 3 8B | 26.9 | #1873 | |
| 9 | Med42-v2-8B | 24.9 | #2558 | |
| 10 | BioMed-R1-8B | 24.2 | ||
| 11 | Gemma 3 4B (IT) | 23.7 | #4139 | |
| 12 | Llama 3.1 8B UltraMedical | 23.1 | ||
| 13 | Adathink-Med-Llama-8B | 22.6 | ||
| 14 | HuatuoGPT-o1-8B | 22.5 | #2983 | |
| 15 | ClinicalGPT-R1-Qwen-7B-EN-preview | 22.5 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=mr-bench-medication-imputation · How It Works · Data refreshed daily, snapshot 2026-11-21.