MedES - Ethical Knowledge: leaderboard
Metric: Accuracy (%; 1,111 multiple-choice questions on Chinese medical ethics and law, one or more correct options among two to five). Source: arxiv.org. Saturation forecast: Estimated already saturated. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek R1 | 60.2 |
| 2 | DeepSeek V3 | 56.5 |
| 3 | GPT-4 Turbo | 43.4 |
| 4 | GPT-4 | 42.8 |
| 5 | GPT-3.5 | 29.3 |
| 6 | DeepSeek-R1-Distill-Qwen-7B | 26.8 |
Interactive version: theaggregate.ai/benchmark?slug=medes-ethical-knowledge · How It Works · Data refreshed daily, snapshot 2026-09-25.