HiMed-West Exam (English): leaderboard
Metric: Accuracy (%; 470 NEET-UG questions in English, zero-shot multiple choice, mean of three runs). Source: arxiv.org. Saturation forecast: Estimated already saturated. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o | 78.1 |
| 2 | Qwen 2.5 14B Instruct | 71.4 |
| 3 | Qwen 2.5 7B Instruct | 62 |
| 4 | Llama 3.1 8B Instruct | 52.6 |
| 5 | aya-23-8B | 38.6 |
Interactive version: theaggregate.ai/benchmark?slug=himed-west-exam-english · How It Works · Data refreshed daily, snapshot 2026-09-25.