RxEval: leaderboard
Inpatient medication recommendation requires clinicians to repeatedly select specific medications, doses, and routes as a patient's condition evolves. Existing benchmarks formulate this task as admission-level prediction over coarse drug codes with multi-hot diagnostic and procedure code inputs, failing to capture the per-timepoint, information-rich nature of real prescribing. We propose RxEval, a
Metric: F1 (self-reported). Source: benchmarklist.com. Saturation forecast: Around July 2027. 17 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 77.1 | #58 |
| 2 | GPT-5.4 | 71.9 | #79 |
| 3 | GPT-5 | 71.8 | #98 |
| 4 | Qwen 3.6 27B | 71.7 | #170 |
| 5 | GPT-5 Mini | 71.3 | #186 |
| 6 | Gemini 3 Flash | 70.6 | #99 |
| 7 | Gemini 2.5 Pro | 70.2 | #152 |
| 8 | Gemini 2.5 Flash | 67.3 | #245 |
| 9 | GPT-4o | 58.9 | #343 |
| 10 | Qwen 2.5 72B Instruct | 56.1 | #454 |
| 11 | Gemma 3 27B (IT) | 55 | #523 |
| 12 | Qwen 2.5 7B Instruct | 53 | #862 |
| 13 | Llama 3.1 8B Instruct | 45.18 | #1035 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=rxeval · How It Works · Data refreshed daily, snapshot 2026-10-20.