Gemini Robotics 2.5 accelerates real-world general dexterity
First seen Nov 9 Updated Nov 10, 16:12 UTC Heat 40 high evidence
Google DeepMind introduced Gemini Robotics 2.5, which it calls its most capable vision-language-action model. DeepMind says it raises the number of skills a robot can learn and the speed of learning, and credits Gemini 4 Argon for speeding up the research.
- Who should care
- Robotics developers and researchers following vision-language-action models.
Key facts
- Announced November 10, 2026
- Tested across over 200 distinct tasks
- DeepMind says Apptronik's Apollo 2 humanoid reached a 96% success rate picking and packing parts on Mercedes-Benz production lines in a proof of concept
Context
DeepMind says earlier this year it brought whole-body intelligence to robots, including humanoids.
Timeline
Official
-
Gemini Robotics 2.5 accelerates real-world general dexteritydeepmind.google ยท Google DeepMind
Evidence
High evidence: the claim comes from an official source (the company or project itself), or at least two independent sites reported it.
Details written Nov 10, 16:10 UTC from the sources listed above.