# Gemini Robotics 2.5 Reaches 96% Success Sorting Metal Parts in a Mercedes-Benz Pilot With Apptronik

DeepMind reports success rates 30% to 100% above its prior baselines across more than 200 tasks and released an adversarial safety benchmark, but the model goes only to robotics partners.

- Published: 2026-11-11T06:08:31.146Z
- Canonical: https://polylog.news/ai/2026-11-11/gemini-robotics-2-5-reaches-96-success-sorting-metal-parts-i
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Google DeepMind](https://deepmind.google/blog/gemini-robotics-2-5-accelerates-real-world-physical-intelligence/), [The Decoder](https://the-decoder.com/google-deepminds-gemini-robotics-2-5-scores-96-percent-sorting-metal-parts-in-a-mercedes-benz-assembly-pilot/), [Interesting Engineering](https://interestingengineering.com/ai-robotics/google-gemini-robotics-2-5-humanoid-factory-trial)

Google DeepMind released Gemini Robotics 2.5, its vision-language-action (VLA) model, which maps camera input and language instructions to motor commands. DeepMind describes it as its most capable robotics model for dexterity, reliability a…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-11-11/gemini-robotics-2-5-reaches-96-success-sorting-metal-parts-i (subscription information: https://polylog.news/pricing).