Alibaba has launched Qwen 2.5-VL, its latest visual-language Artificial Intelligence model, claiming that it outperforms DeepSeek V3.
According to Alibaba, this update is a significant improvement from its predecessor, Qwen2-VL. “Qwen 2.5-Max outperforms almost across the board GPT-4o, DeepSeek-V3 and Llama-3.1-405B,” Alibaba’s cloud unit said in an announcement posted on its official WeChat account.
The flagship model, Qwen2.5-VL-72B-Instruct, is now accessible through the Qwen Chat platform, while the entire Qwen2.5-VL series is available on Hugging Face and Alibaba’s open-source community Model Scope.
Read also: DeepSeek copied OpenAI — Experts
Alibaba reveals that Qwen2.5-VL demonstrates remarkable multimodal capabilities, excelling in advanced visual comprehension of texts, charts, diagrams, graphics, and layouts within images.
It can also understand videos for longer than an hour and answer video-related questions while accurately identifying specific segments down to the exact second.
According to reports, Qwen 2.5-Max’s release, on the first day of the Lunar New Year when most Chinese people are off work and with their families, is unusual and points to the pressure DeepSeek’s meteoric rise in the past three weeks has placed on not just overseas rivals, but also its domestic competition.
Join BusinessDay whatsapp Channel, to stay up to date
Open In Whatsapp
