Alibaba Cloud Releases Latest AI Models For Enhanced Visual Understanding

(RTTNews) - Chinese tech giant Alibaba Cloud on Wednesday unveiled its latest visual-language model, Qwen2.5-VL, which it claims to be a significant improvement from its predecessor, Qwen2-VL.

The open-source, multimodal model is offered in various sizes, ranging from 3 billion, 7 billion to 72 billion parameters, and includes both base and instruction-tuned versions.

"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, referring to OpenAI and Meta's most advanced open-source AI models.

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.

Alibaba claims 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 longer than an hour and answer video-related questions, while accurately identifying specific segments down to the exact second.