MedES - Ethical Knowledge: leaderboard
Multiple-choice set of MedES (Jin et al., Shanghai Jiao Tong University, AAAI 2026): 1,111 questions on Chinese medical-ethics and legal norms, each with one or more correct options among two to five. Accuracy in percent; higher is better.
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 | Overall rank |
|---|---|---|---|
| 1 | DeepSeek R1 | 60.2 | #467 |
| 2 | DeepSeek V3 | 56.5 | #705 |
| 3 | GPT-4 Turbo | 43.4 | #1002 |
| 4 | GPT-4 | 42.8 | #996 |
| 5 | GPT-3.5 | 29.3 | #2430 |
| 6 | DeepSeek-R1-Distill-Qwen-7B | 26.8 | #8045 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=medes-ethical-knowledge · How It Works · Data refreshed daily, snapshot 2026-11-12.