aiqbench analysis
Google DeepMind has released Gemini Robotics 2.5, a significant advancement in vision-language-action models designed to enhance robotic dexterity and reliability in unstructured environments. The update demonstrates improved performance across over 200 distinct tasks, including real-world validation on automotive production lines where it achieved a 96% success rate for pick-and-pack operations. This release marks a critical step toward deploying autonomous physical agents capable of handling delicate objects and complex daily activities with greater safety.
Gemini Robotics 2.5: Accelerating Physical Intelligence

From Physical Intelligence
ExcerptToday, we are introducing Gemini Robotics 2.5, our most capable vision-language-action (VLA) model to date. Gemini Robotics 2.5 increases both the breadth of skills a robot can learn and the speed at which it can acquire them. This enhances dexterity, reliability, and safety to help robots step out of the lab and into more unstructured, real-world environments, where they can assist people with a greater range of tasks.
Earlier this year, we brought whole-body intelligence to robots of many types, including humanoids. Now, in large part thanks to Gemini 4 Argon's ability to accelerate robotics research, we have further pushed the frontier of physical intelligence.
Excerpt shown under the publisher's RSS terms · 105 words · full text and figures are on the publisher's site
Other coverage of this story
- Physical Intelligence · this article
- GIGAZINE · Google announces Gemini Robotics 2.5, an AI for robots.
Related coverage

A wander through adult intelligence amplification...
LessWrong · Nov 18, 2026

PyTorch Conference North America 2026: Accelerating Open Intelligence Together
PyTorch · Oct 22, 2026

Built Technologies builds an AI-powered document intelligence solution on AWS to power agents across real estate finance
AWS · Jul 15, 2026

Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · Aug 27, 2026