RxEval - Exact Match: leaderboard
Metric: Exact match (%): the selected option set equals the set of medication-dose-route triples actually prescribed, over 1,547 RxEval multiple-answer questions, zero-shot at temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 | 48.7 |
| 2 | GPT-5.4 | 47.9 |
| 3 | Gemini 3.1 Pro (Preview) | 46.1 |
| 4 | GPT-5 Mini | 42.7 |
| 5 | Qwen 3.6 27B | 40 |
| 6 | Gemini 2.5 Flash | 38 |
| 7 | Gemini 2.5 Pro | 37.6 |
| 8 | Gemini 3 Flash | 36.1 |
| 9 | GPT-4o | 21.7 |
| 10 | Qwen 2.5 7B Instruct | 10.1 |
| 11 | Qwen 2.5 72B Instruct | 9.9 |
| 12 | Gemma 3 27B (IT) | 9.8 |
| 13 | Llama 3.1 8B Instruct | 1.36 |
Interactive version: theaggregate.ai/benchmark?slug=rxeval-exact-match · How It Works · Data refreshed daily, snapshot 2026-10-07.