CareQA-Vision - Open-Ended: leaderboard
Metric: Judge score (%; 136 open-ended image-based questions from MIR and EIR exams, majority of three LLM judges scoring 0, 0.5 or 1). Source: arxiv.org. Saturation forecast: Around December 2026. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 74.63 |
| 2 | GLM-4.5V | 64.71 |
| 3 | Qwen 2 VL 72B Instruct | 45.59 |
| 4 | Qwen 3 VL 30B A3B Instruct | 43.75 |
| 5 | HuluMed-7B | 43.38 |
| 6 | Qwen 3 VL 8B Instruct | 38.24 |
| 7 | Lingshu-7B | 31.25 |
| 8 | Qwen 2 VL 7B Instruct | 26.47 |
Interactive version: theaggregate.ai/benchmark?slug=careqa-vision-open-ended · How It Works · Data refreshed daily, snapshot 2026-09-25.