小米发布 MiMo-V2.6 Pro 与 Flash 全模态模型
From Vibe Coding to Vibe World. 🌍
小米 MiMo 发布 MiMo-V2.6 Pro 与 Flash 两款全模态模型,结合 3D 空间推理、多模态感知与 computer use,可把文本、图像或视频转成可玩的 3D 世界,并支持 Blender 场景创建、仿真中控制 Franka Panda 机械臂以及桌面工具操作。官方称 Pro 在多数智能体基准上与 Claude Opus 5、GPT-5.6 Sol 相当,Artificial Analysis Intelligence Index 得分 46,为开源模型最高,API 定价与 V2.5 持平。团队同时开源 Pro、Flash、MiMo-V2.6-Distill-Qwen-9B、技术报告、7K+ RL 任务环境、端到端 RL 框架与可组合 mini-harness,并上线 MiMo Desktop 与订阅方案。
正文
当前显示原文,中文全文译文尚未就绪。
From Vibe Coding to Vibe World. 🌍
MiMo-V2.6 brings together 3D spatial reasoning, multimodal perception and computer use to build and interact with richer environments.
🔹 Turn text, images or video into playable 3D worlds, coordinating agents to build scenes, write interaction logic and refine the results 🔹 Create Blender objects and scenes for animation, 3D printing and games 🔹 Control a Franka Panda arm in simulation through visual feedback 🔹 Use desktop tools to search, edit and process data — then inspect the results and adjust its next actions Build. Observe. Refine.