阿里发布 Qwen3.8-Omni-Flash 多模态模型，音频视频理解与工具使用能力提升
🚀 Meet Qwen3.8-Omni-Flash, Qwen's first omni-modal model built around agentic capabilities! Native...
阿里新出的 Qwen3.8-Omni-Flash 模型，音频视频理解能力更强，还能用工具自动编辑视频、翻译视频，比之前的版本更便宜，适合做长视频处理。
这是阿里推出的 Qwen3.8-Omni-Flash 模型，它具备音频视频理解、推理和工具使用能力。该模型在 WildClawBench-MM & UniClawBench 基准测试中，平均在代理性能上比 Qwen3.5-Omni-Plus 高 19.5 分。它支持 1M-token 的上下文，在 OmniVideoBench 上定位关键片段的准确率更高，比静态理解节省 51.8% 的 token，视频输入成本比 Qwen3.5-Omni-Plus 降低约 89%。
🚀 Meet Qwen3.8-Omni-Flash, Qwen's first omni-modal model built around agentic capabilities! Native...
🚀 Meet Qwen3.8-Omni-Flash, Qwen's first omni-modal model built around agentic capabilities! Native audio-video understanding, reasoning, and tool use come together in one model: understand the content, plan the task, execute with tools, and deliver the result. Highlights: 🥳 - Audio-video intelligence that gets things done: jointly reason over what's seen and heard, and orchestrate tools across long workflows to auto-edit vlogs, translate short videos, and turn movies into recaps. - A major leap: approaching Gemini 3.8 Flash in audio-video capabilities; +19.5 points on average in agent performance across WildClawBench-MM & UniClawBench. - 1M-token context with agentic perception: actively explore long videos and locate key moments with higher accuracy, using 51.8% fewer tokens than static understanding on OmniVideoBench. Video input costs are reduced by about 89% compared with Qwen3.5-Omni-Plus, making long-form audio-video understanding and agentic workflows more affordable than ever. To help you build apps around Omni, we're also open-sourcing Qwen-MM-Plugins and Qwen-Live Harness! 🛠️ We can't wait to see what you build with Qwen3.8-Omni-Flash! 👀 - Bl qwen.ai/blog?id=qwen3.… kqYF - Qwenclo qwencloud.com/models/qwen3.8… LAnD - Qwen Stud chat.qwen.ai aVNZ - A alibabacloud.com/help/en/model-… 5YUt - Qwen-MM-Plugi github.com/QwenLM/Qwen-MM… DP3d - Qwen-Live Harness: coming s github.com/QwenLM/Qwen-Li… Ibdy 💬 46 🔄 74 ❤️ 534 👀 18989 📊 129 ⚡
