Share your thoughts, 1 month free Claude Pro on usSee more

Multiple Choice Question Answering on CareQA-V MCQ

80.61Accuracy

GPT-5.2

Updated 27d ago

Evaluation Results

Method	Links
GPT-5.2 2026.06		80.61
Aloe-Vision-72B 2026.06		77.58
Aloe-Vision-72B-AR 2026.06		75.76
Qwen2-VL-72B-Instruct 2026.06		72.73
GLM-4.5V 2026.06		72.73
Qwen3-VL-30B-A3B-Instruct 2026.06		71.52
Lingshu-32B 2026.06		64.85
Hulu-Med-32B 2026.06		63.64
Aloe-Vision-7B-AR 2026.06		60.61
MiMo-VL-7B-RL 2026.06		59.39
Hulu-Med-7B 2026.06		59.39
Qwen3-VL-8B-Instruct 2026.06		58.79
Lingshu-7B 2026.06		56.97
Aloe-Vision-7B 2026.06		56.36
Kimi-VL-A3B-Instruct 2026.06		55.15
HuatuoGPT-Vision-34B 2026.06		54.55
Qwen2-VL-7B-Instruct 2026.06		51.52
HuatuoGPT-Vision-7B 2026.06		50.3
Chiron-o1-8B 2026.06		47.27