HiMed (English): leaderboard
Metric: Accuracy (%; mean of the four English sets, zero-shot multiple choice, mean of three runs). Source: arxiv.org. Saturation forecast: Estimated already saturated. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 14B Instruct | 61.1 |
| 2 | GPT-4o | 59.9 |
| 3 | Qwen 2.5 7B Instruct | 54.6 |
| 4 | Llama 3.1 8B Instruct | 50.8 |
| 5 | aya-23-8B | 32 |
Interactive version: theaggregate.ai/benchmark?slug=himed-english · How It Works · Data refreshed daily, snapshot 2026-09-25.