---
id: "2026-11-10-gemini-robotics-2-5-asimov-jailbreak"
url: "https://postcutoff.com/e/2026-11-10-gemini-robotics-2-5-asimov-jailbreak/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2026-11-10"
date_precision: day
category: robotics
importance: 3
confidence: high
status: [Confirmed]
sources: 3
editor: human editor
human_review: null
version: "2026-11-12"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2026-11-10-gemini-robotics-2-5-asimov-jailbreak/

# Google DeepMind releases Gemini Robotics 2.5 to partners and open-sources the ASIMOV-Jailbreak robot-safety benchmark

On Nov 10, 2026 Google DeepMind released Gemini Robotics 2.5 to its robotics partners, reporting 30-100% higher success than earlier baselines on over 200 tasks and a 96% success rate for Apptronik Apollo 2 humanoids sorting brackets on Mercedes-Benz production lines in a proof of concept. It also open-sourced ASIMOV-Jailbreak, a benchmark of disguised unsafe requests to robots.

## Key facts
- Evaluated on 200+ distinct tasks: 30-100% higher success than previous baselines depending on task type, tasks finished 20-30% faster (DeepMind)
- Mercedes-Benz proof of concept: Apptronik Apollo 2 humanoids sorted automotive brackets into trays for assembly with 96% success
- Skills shown: tool use (serving food with tongs), deformable objects such as laundry, delicate items; runs on Apollo 2 and the Franka Duo platform
- Safety: inference-time reasoning guidance improved safe task completion by 33% around obstacles and 43% around nearby people; on ASIMOV-Jailbreak (hundreds of prompts disguising unsafe requests across dozens of scenes), Gemini 4 Argon resisted 99.5% vs 82% for Gemini Robotics-ER 2
- Gemini 4 Argon generated simulated practice runs and digital twins used in development
- Availability: robotics partners only; no public API mentioned
- Apptronik CEO Jeff Cardenas: 'This is what we built Apollo for: useful work alongside people in real industrial settings'

## What happened

DeepMind's robotics line moved from the Gemini Robotics 2 / ER 2 models to 2.5, with a factory proof of concept as the headline result.
The success figures are DeepMind's own.

## Why it matters

A frontier lab reporting humanoids at 96% on a real production-line task, together with an open benchmark for tricking robots into
unsafe actions, marks the step from lab demos toward industrial pilots.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): 194 days after its cutoff
- Claude Opus 5.5 (training cutoff June 2026): 133 days after its cutoff
- Gemini 4 Hydrogen (training cutoff March 2026): 224 days after its cutoff
- Grok 4.7 (training cutoff May 2026): 163 days after its cutoff

## Sources

1. [Google DeepMind: Gemini Robotics 2.5 accelerates real-world general dexterity](https://deepmind.google/blog/gemini-robotics-2-5-accelerates-real-world-physical-intelligence/) (deepmind.google, official)
2. [Google DeepMind on X (475k views)](https://x.com/GoogleDeepMind/status/2120169787896525104) (x.com, official)
3. [Ars Technica: 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/) (arstechnica.com, press)

## Changes

- 2026-11-12 (filed): Created (news agent)

## Related

- 2026-11-12: [Google releases Gemini 4 Hydrogen, a fast Gemini 4 model that edges past Argon, and brings it to Search for everyone](https://postcutoff.com/e/2026-11-12-gemini-4-hydrogen/index.md)
- Archived: 1 post, listed in https://postcutoff.com/e/2026-11-10-gemini-robotics-2-5-asimov-jailbreak/index.json