MR-Bench - Medication Imputation: leaderboard
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 April 2027. 24 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 55 |
| 2 | GPT-5 | 54.4 |
| 3 | DeepSeek V3.2 (Thinking) | 48.4 |
| 4 | Qwen 3 Max | 44.6 |
| 5 | GPT-4o | 36.3 |
| 6 | Qwen 3 4B 2507 (Thinking) | 27.2 |
| 7 | Qwen 3 8B | 26.9 |
| 8 | Gemma 3 4B (IT) | 23.7 |
| 9 | MedGemma-4B | 21.4 |
| 10 | Qwen 2.5 7B Instruct | 21.3 |
| 11 | Llama 3 8B Instruct | 16.6 |
| 12 | Llama 3.1 8B Instruct | 15.3 |
Interactive version: theaggregate.ai/benchmark?slug=mr-bench-medication-imputation · How It Works · Data refreshed daily, snapshot 2026-10-07.