# Google DeepMind — Gemini Robotics 2.5 accelerates real-world general dexterity

- Company: Google DeepMind (deepmind.google)
- Announced: 2026-11-09T19:51:47+00:00
- Category: new-model
- Coverage: 3 outlets
- Announcement: yes
- Group: models
- Source: https://deepmind.google/blog/gemini-robotics-2-5-accelerates-real-world-physical-intelligence/
- Record: https://forck.live/items/34057-gemini-robotics-2-5-accelerates-real-world-general-dexterity
- Subject: Gemini
- Models affected: Gemini Robotics 2.5, Gemini Robotics ER, Gemini 4 Argon, Gemini Robotics ER 2

Google DeepMind introduced Gemini Robotics 2.5, a vision-language-action model it says is its most capable to date, widening the range of skills robots can learn and how fast they acquire them. The company evaluated the model across more than 200 distinct tasks, including serving food with tongs, tying a bow on a gift box and pipetting liquid, and says it reaches a 30% to 100% higher success rate than previous baselines while finishing tasks 20% to 30% faster. In a proof-of-concept on Mercedes-Benz production lines in Kecskemét, Hungary, and Sindelfingen, Germany, Apptronik's Apollo 2 humanoid used the model to pick and pack automotive parts with a 96% success rate. DeepMind says inference-time reasoning guidance steers the robot around physical hazards in real time, lifting safe task completion by 33% around obstacles and 43% around nearby people. The company is also releasing ASIMOV-Jailbreak, an open-source benchmark of hundreds of prompts that disguise unsafe requests across dozens of scenes, on which Gemini 4 Argon reaches 99.5% jailbreak resistance against an 82% baseline for Gemini Robotics ER 2. Gemini Robotics 2.5 is rolling out to the company's robotics partners.

## Evidence

Verbatim from https://deepmind.google/blog/gemini-robotics-2-5-accelerates-real-world-physical-intelligence/:

> Compared to previous baselines, Gemini Robotics 2.5 achieves a 30% to 100% higher success rate depending on the type of task, while completing tasks 20% to 30% faster.

## Around this story

Outlets this record can name and link:

- Tech Times — Gemini Robotics 2.5 Reports 96% Success Sorting Mercedes Car Parts but Publishes No Trial Count: https://techtimes.com/articles/330432/20261111/gemini-robotics-25-reports-96-success-sorting-mercedes-car-parts-publishes-no-trial-count.htm
- Tech Times — DeepMind Launches Gemini Robotics 2.5, but 99.5% Robot Jailbreak Score Is for Gemini 4 Argon: https://techtimes.com/articles/330435/20261111/deepmind-launches-gemini-robotics-25-995-robot-jailbreak-score-gemini-4-argon.htm
- Madrobot — Google DeepMind’s new robot brain has humanoids packing car parts at Mercedes-Benz: https://madrobot.blog/2026/11/10/gemini-robotics-2-5-humanoids-mercedes-factory
- Gigazine — Googleがロボット用AI「Gemini Robotics 2.5」を発表: https://gigazine.net/news/20261111-gemini-robotics-2-5

---

Record: https://forck.live/items/34057-gemini-robotics-2-5-accelerates-real-world-general-dexterity
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
