Gemini Robotics 2.5 launches with enhanced everyday skills
Gemini Robotics 2.5 launches with enhanced everyday skills
Google DeepMind has unveiled Gemini Robotics 2.5, its latest vision-language-action model designed to teach robots hundreds of tasks more quickly and broadly. Announced on November 10, 2026, the model focuses on advanced tool use and delicate handling, showing improved success rates (30% to 100%) and speed (20% to 30% faster) compared to earlier versions. A proof-of-concept deployment on a Mercedes-Benz production line using Apptronik's Apollo 2 robot achieved a 96% success rate in sorting automotive parts. The release also includes safety upgrades for operator control and resistance to adversarial manipulation.
Source: Robotics — Web news discovery · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
Reported success rate
96%
Reported trials
View original evidence
st run The most concrete result came from a factory floor rather than a lab. Apptronik’s Apollo 2 humanoid robot ran a proof-of-concept on a Mercedes-Benz production line. Apollo 2 handled sorting and packing car components. It hit a 96% success rate during that trial. The model is rolling out to partners in the robotics industry. The company is presenting Gemini Robotics 2.5 as a versatile dexterity layer that can w
Open source S5Reported success rate
30%
View original evidence
t, the company evaluated the model on 200 distinct tasks. Those tests emphasized advanced tool use and delicate handling, the kind of work where a clumsy grip ruins the outcome. The performance numbers are the part that stands out. Compared with earlier models, success rates improved by 30% to 100% across various tasks. Speed moved too. Task completion ran 20% to 30% faster than prior iterations. The Mercedes-Benz te
Open source S4Reported success rate
20%
View original evidence
t, the company evaluated the model on 200 distinct tasks. Those tests emphasized advanced tool use and delicate handling, the kind of work where a clumsy grip ruins the outcome. The performance numbers are the part that stands out. Compared with earlier models, success rates improved by 30% to 100% across various tasks. Speed moved too. Task completion ran 20% to 30% faster than prior iterations. The Mercedes-Benz te
Open source S4task count
200
Reported trials
View original evidence
t, the company evaluated the model on 200 distinct tasks. Those tests emphasized advanced tool use and delicate handling, the kind of work where a clumsy grip ruins the outcome. The performance numbers are the part that stands out. Compared with earlier models, success rates improved by 30% to 100% across various tasks. Speed moved too. Task completion ran 20% to 30% faster than prior iterations. The Mercedes-Benz te
Open source S4Reported success rate
100%
View original evidence
t, the company evaluated the model on 200 distinct tasks. Those tests emphasized advanced tool use and delicate handling, the kind of work where a clumsy grip ruins the outcome. The performance numbers are the part that stands out. Compared with earlier models, success rates improved by 30% to 100% across various tasks. Speed moved too. Task completion ran 20% to 30% faster than prior iterations. The Mercedes-Benz te
Open source S4robot model version
2.5
release date
2,026
View original evidence
, from folding laundry to sorting automotive parts. What Gemini Robotics 2.5 actually does Google DeepMind announced the model on November 10, 2026. It is a vision-language-action model, or VLA, which is the category the company is pushing hard. The headline goal of this release is twofold. Google DeepMind wants robots to learn a wider range of tasks, and it wants them to pick those tasks up more quickly. To test tha
Open source S3
- paper: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
st run The most concrete result came from a factory floor rather than a lab. Apptronik’s Apollo 2 humanoid robot ran a proof-of-concept on a Mercedes-Benz production line. Apollo 2 handled sorting and packing car components. It hit a 96% success rate during that trial. The model is rolling out to partners in the robotics industry. The company is presenting Gemini Robotics 2.5 as a versatile dexterity layer that can w
Open source S5
t, the company evaluated the model on 200 distinct tasks. Those tests emphasized advanced tool use and delicate handling, the kind of work where a clumsy grip ruins the outcome. The performance numbers are the part that stands out. Compared with earlier models, success rates improved by 30% to 100% across various tasks. Speed moved too. Task completion ran 20% to 30% faster than prior iterations. The Mercedes-Benz te
Open source S4
Gemini Robotics 2.5 launches with enhanced everyday skills
Open source S1
, from folding laundry to sorting automotive parts. What Gemini Robotics 2.5 actually does Google DeepMind announced the model on November 10, 2026. It is a vision-language-action model, or VLA, which is the category the company is pushing hard. The headline goal of this release is twofold. Google DeepMind wants robots to learn a wider range of tasks, and it wants them to pick those tasks up more quickly. To test tha
Open source S3
Source：Robotics — Web news discovery · cryptobriefing.com