Google DeepMind Introduces Gemini Robotics 2.5 for Robot Skills
Understand the event
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.
Generated by AI from reports · Updated 2 days ago
Read next
More changes in today’s briefingGoogle DeepMind Introduces Gemini 4 Hydrogen for Fast Agentic WorkflowsReport timeline
Follow the reports to explore different sides of the event.
- The DecoderPicksGoogle DeepMind Introduces Gemini Robotics 2.5 for Robot Control
Google DeepMind introduced Gemini Robotics 2.5, a vision-language-action model for robot control, and tested it with Apptronik and Mercedes-Benz on active production lines in Hungary and Germany. The Apollo 2 humanoid robot sorted metal parts into trays for vehicle assembly, with Google DeepMind reporting a 96 percent success rate in the pilot. The company says the model is rolling out to Agile, Apptronik, and Mercedes-Benz.
- Google DeepMind · XPicksGoogle DeepMind Announces Gemini Robotics 2.5 for Physical AI
Google DeepMind announces Gemini Robotics 2.5, describing it as physical AI able to learn hundreds of everyday skills. Examples include folding laundry, serving pastries, and autonomously sorting car parts on a factory floor.
- Google DeepMind Reveals Gemini Robotics 2.5 and ASIMOV-Jailbreak Benchmark
Google DeepMind has revealed Gemini Robotics 2.5, a new version of its vision-language-action model for generating robot actions. The report says it was evaluated on more than 200 activities, including serving food with tongs and using a pipette, and describes an Apptronik Apollo 2 robot tying a bow. DeepMind is also preparing an open source safety benchmark for robots operating alongside people.
- Google DeepMindPicksGoogle DeepMind Introduces Gemini Robotics 2.5 for Real-World Dexterity
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.
Keep up with AI, one email a day
Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue
Event heat trend
- Current within comparable coverage
- 3
- Peak within comparable coverage
- 1011/11 00:00 (UTC+8)
- 24-hour change
- -50%
Trends compare the same continuously observed participants, which may cover fewer sources than current heat. Point or click to inspect hourly heat, or use left and right arrow keys.