CareQA-Vision - Open-Ended - Nursing: leaderboard

Metric: Judge score (%; 28 open-ended image-based questions from EIR nursing exams, majority of three LLM judges scoring 0, 0.5 or 1). Source: arxiv.org. Saturation forecast: Around December 2026. 18 models tracked.

Top models

#ModelScore
1GLM-4.5V51.79
2Qwen 2 VL 72B Instruct32.14
3Qwen 3 VL 8B Instruct26.79
4Qwen 3 VL 30B A3B Instruct23.21
5HuluMed-7B23.21
6Lingshu-7B17.86
7Qwen 2 VL 7B Instruct16.07

Interactive version: theaggregate.ai/benchmark?slug=careqa-vision-open-ended-nursing · How It Works · Data refreshed daily, snapshot 2026-09-25.