- Who
- Google DeepMind
- What
- announces Gemini Robotics 2.5, a physical AI model
- Quote
Today, we are introducing Gemini Robotics 2.5, our most capable vision-language-action (VLA) model to date.
What happened
Google DeepMind introduced Gemini Robotics 2.5, a vision-language-action model designed to help robots learn a broader range of skills faster. Across 200 distinct tasks, it achieved success rates 30% to 100% higher than previous baselines and completed tasks 20% to 30% faster. In a proof of concept on Mercedes-Benz production lines, Apptronik’s Apollo 2 humanoid sorted automotive parts with a 96% success rate.
Why it matters
The post reports task success and speed gains alongside a factory pilot and safety evaluations, giving readers several concrete measures of the model’s reported performance.
Read next
See the full storyGoogle DeepMind Introduces Gemini Robotics 2.5 for Robot SkillsReported by 2 sources
The story so far
Google DeepMind introduced Gemini Robotics 2.5, a vision-language-action model now rolling out to its robotics partners. The company says it is designed to help robots learn a broader range of skills faster. Across 200 tasks, the model achieved success rates 30% to 100% higher than previous baselines and completed tasks 20% to 30% faster, according to Google DeepMind. In a proof of concept on Mercedes-Benz production lines, Apptronik’s Apollo 2 humanoid sorted automotive parts with a 96% success rate.