📰 Google DeepMind Releases Gemini Robotics 2.5: 30% to 100% Higher Success Across 200 Tasks, a 96% Parts-Kitting Rate for Apptronik Apollo 2 on Mercedes-Benz…
On November 10, Google DeepMind released Gemini Robotics 2.5, which it calls its most capable vision-language-action (VLA) model so far. Across more than 200 evaluated tasks, DeepMind reports a 30% to 100% higher success rate than earlier baselines depending on the task type, with tasks finished…
💬 What's your take? Join the discussion in the comments.
Read the original Chinese version
📰 Google DeepMind 发布 Gemini Robotics 2.5：200 项任务成功率提升 30%–100%，Apptronik Apollo 2 在奔驰产线分拣零件成功率 96%，并开源机器人越狱测评…
Google DeepMind 11 月 10 日发布 Gemini Robotics 2.5，称其为迄今最强的视觉-语言-动作（VLA）模型。官方在 200 多项任务上评测，相比此前基线成功率按任务类型提高 30% 到 100%，完成速度快 20% 到 30%。
💬 你怎么看？欢迎在评论区讨论。