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

Vision-Centric Reasoning on MuirBench

68Accuracy

GPT-4o

Updated 1mo ago

Evaluation Results

Method	Links
GPT-4o 2025.09		68
Gemini2.0-Flash 2025.09		64.6
MM-Eureka-Qwen-7B 2025.09		61.1
VisionZero-Qwen-7B (Real-World) 2025.09		59.4
VisionZero-Qwen-7B (Chart) 2025.09		59.2
Qwen2.5-VL-7B 2025.09		58.2
VisionZero-Qwen-7B (CLEVR) 2025.09		58.2
ViGaL-Snake+Rotation 2025.09		57.8
VLAA-Thinker-7B 2025.09		57.1
OpenVLThinker-7B 2025.09		52.8
R1-OneVision-7B 2025.09		46.3