AI 导读
阿里发布全模态模型 Qwen3.8-Omni-Flash，支持音频与视频理解，具备 1M token 上下文窗口，在 WildClawBench-MM 和 UniClawBench 上的表现接近 Gemini 3.8 Flash。随附图片将其定位为 Native Agent，称其先理解查询，再决定如何听或看，无需看完整段视频。
正文
Alibaba released Qwen3.8-Omni-Flash, a new omni-modal model with audio and video understanding.
Qwen3.8-Omni-Flash comes with 1M-token context window and performance close to Gemini 3.8 Flash on WildClawBench-MM & UniClawBench. https://t.co/jata5ZHXcE
来源：@testingcatalog · x.com