阿里通义 7 大模型霸榜全球开源前十，千问 Qwen3-Omni 登顶

On September 28th, the world's largest AI open-source community Hugging Face announced the latest model rankings, with seven models from Alibaba Tongyi making it into the top ten open-source models globally, nearly sweeping the board. The newly open-sourced multimodal large model Qwen3-Omni topped the list. It is understood that Qwen3-Omni is Alibaba's latest open-sourced multimodal large model, capable of processing four different types of data: text, images, audio, and video, and can "listen, speak, and write" like a human. While achieving strong audio and audio-visual capabilities, Qwen3-Omni maintains stable performance in single-modal text and image processing, marking the first time this training effect has been achieved in the industry. In the future, it will be deployable in scenarios such as in-vehicle systems, smart glasses, and mobile phones