QVQ-Max: Think with Evidence

Qwen · 1 year ago

Alibaba's Qwen team released QVQ-Max, a visual reasoning model that analyzes images and videos to solve problems across mathematics, coding, and creative tasks. The model shows continuous accuracy improvements on the MathVision benchmark as its reasoning process length increases, demonstrating enhanced problem-solving capabilities. The release enables broader applications in workplace productivity, education, and daily life assistance through improved visual understanding and analytical reasoning.