Reported News
Google DeepMind introduces Gemini Robotics 2.5, its most capable vision-language-action model
Google DeepMind introduced Gemini Robotics 2.5 on Nov 10, 2026, calling it "our most capable vision-language-action (VLA) model to date." Google reports 30% to 100% higher success rates than previous baselines across 200 tasks, and says the model is rolling out to robotics partners.
- Changes reported
- 6
- listed below, each from a source we read
- We tested
- Not tested yet
- reported from sources; we did not run it ourselves
- Gaps we flag
- 4
- things we could not verify
- Sources
- 1
- 1 primary, linked below
What changed
| # | What the source says | Status |
|---|---|---|
| 01 | Google DeepMind says Gemini Robotics 2.5 is its most capable vision-language-action model to date and is rolling out to its robotics partners; no public API or pricing is announced. | Reported |
| 02 | Across 200 distinct tasks such as serving food with tongs, tying a bow and pipetting a liquid, Google reports a 30% to 100% higher success rate than previous baselines and 20% to 30% faster completion. | Reported |
| 03 | In a proof-of-concept on Mercedes-Benz production lines in Kecskemét, Hungary, and Sindelfingen, Germany, Apptronik's Apollo 2 humanoid did automotive kitting with a 96% success rate, per Google. | Reported |
| 04 | Google says inference-time reasoning guidance raised safe task completion by 33% around obstacles and 43% around nearby people in its evaluations. | Reported |
| 05 | DeepMind is releasing ASIMOV-Jailbreak, an open-source robotics jailbreak benchmark; it reports Gemini 4 Argon at 99.5% jailbreak resistance versus 82% for Gemini Robotics ER 2. | Reported |
| 06 | Google credits Gemini 4 Argon with speeding development by generating thousands of simulated practice runs and digital twins from real camera scenes. | Reported |
reported by the sourcemeasured or run by usnot verified
Primary source: Google DeepMind blog: Gemini Robotics 2.5 accelerates real-world general dexterity. We are the fast, independent index; the vendor’s own page is the source of record for this release.
In the source’s words
“Today, we are introducing Gemini Robotics 2.5, our most capable vision-language-action (VLA) model to date.”
“Gemini Robotics 2.5 is rolling out to our robotics partners”
What we have not verified
- We did not run the model; every number is from Google's own evaluations.
- Google does not name which partners get access, when it will be broadly available, or any API model id or price.
- The 96% kitting figure is from a proof-of-concept pilot; Google gives no number of attempts or duration, and we did not check Mercedes-Benz or Apptronik statements.
- The 99.5% jailbreak resistance figure is for Gemini 4 Argon, not for Gemini Robotics 2.5 itself.
This brief is Reported: written from the sources below, not from running the release ourselves.
Sources
- Google DeepMind blog: Gemini Robotics 2.5 accelerates real-world general dexterityprimary source · fetched 2026-11-10
Related
Spotted an error? See our corrections policy or email the address on the contact page. Markdown version for agents: /news/gemini-robotics-2-5-vla-model.md
Want these briefs in your Google Top Stories? Add Agentic Weekly as a preferred source on Google.
Newsletter
The Weekly Verdict. Free, every Monday.
A free email every Monday: the week's few big AI releases, then 5 short use cases for the new models, each with a prompt you can paste.
Free. Double opt-in. One click to unsubscribe.