Meta 发布开源模型 Muse Spark Open,已上线 Agent Arena 测评
Meta 新开源的 Muse Spark Open,816B 总参数、百万 token 上下文,主打编程和智能体任务,现在已经能在 Agent Arena 亲手测了。
Meta 发布 Muse Spark Open,称其为目前美国最强的开源权重模型。该模型总参数 816B、激活参数 42B,支持 1M token 上下文窗口,原生支持文本、图像、视频、音频多模态。官方定位其擅长长程任务、复杂软件工程和多步推理。模型已进入 Agent Arena,可通过网页搜索、文件系统、终端工具完成工作流,同时也在 Code Arena 的 WebDev、Image-to-WebDev、Text 和 Vision 赛道可用,评测分数尚未公布。
Muse Spark Open by @AIatMeta is now in the Arena. Head to Agent Arena to test it out, scores coming soon! In Agent Arena, we measure models on millions of real-world, long-horizon agentic tasks from a global community of users. Models can access web search, filesystem, and terminal tools to complete complex workflows. The leaderboard measures model performance on outcomes relative to the average model using a causal tracing methodology. Muse Spark Open is also available in Code Arena: WebDev, Image-to-WebDev, Text, and Vision. AI at Meta @AIatMeta Today we’re releasing Muse Spark Open, the most capable US open-weight model to date. Built for coding and agentic work, it excels at long-horizon tasks, complex software engineering, and multi-step reasoning. Key Model Specs: → 816B total / 42B active parameters → 1M token context window → Natively multimodal across text, image, video, audio 🔗 View Quoted Tweet 💬 8 🔄 6 ❤️ 46 👀 4637 📊 10 ⚡