# DeepMind reveals Gemini Robotics 2.5 and open safety benchmark "ASIMOV-jailbreak"

> HelixNews · Web page: https://helixnews.one/story/5713 · All pages for agents: https://helixnews.one/llms.txt

2 outlets covering · First listed: Ars Technica, Nov 10, 2026, 9:00 AM · Read it: <https://arstechnica.com/google/2026/11/deepmind-reveals-gemini-robotics-2-5-and-open-safety-benchmark-asimov-jailbreak/>

The new model is up to twice as successful at some tasks.

## Who's covering it

In the order they published:

- Nov 10, 2026, 9:00 AM: [DeepMind reveals Gemini Robotics 2.5 and open safety benchmark "ASIMOV-jailbreak"](<https://arstechnica.com/google/2026/11/deepmind-reveals-gemini-robotics-2-5-and-open-safety-benchmark-asimov-jailbreak/>) — Ars Technica (Digital news, United States)
  The new model is up to twice as successful at some tasks.
- Nov 10, 2026, 9:10 AM: [Google DeepMind unveils Gemini Robotics 2.5 with ASIMOV-Jailbreak safety benchmark](<https://cryptobriefing.com/google-deepmind-gemini-robotics-2-5-asimov/>) — Crypto Briefing (Specialist)
  The advancements in AI robotics and safety benchmarks could redefine industry standards, enhancing both operational efficiency and regulatory frameworks.