Google’s Gemini Robotics 2.5 scores 96% in factory trial after tackling 200 tasks

Google DeepMind has introduced Gemini Robotics 2.5, a new model designed to help robots learn physical tasks faster, handle delicate objects, and operate more reliably in real-world environments. The model achieved a 96 percent success rate in a factory proof-of-concept involving Apptronik’s Apollo 2 humanoid robots on Mercedes-Benz production lines. The robots autonomously sorted automotive parts from bulk bins into organized trays, preparing components in the sequence required for vehicle assembly. The trial took place at production facilities in Kecskemét, Hungary, and Sindelfingen, Germany. Google said the work could help automate repetitive and physically demanding tasks while allowing factory technicians to focus on more complex assembly work. Gemini Robotics 2.5 is the company’s latest vision-language-action (VLA) model, which translates visual information and instructions into physical robot movements. It is currently rolling out to Google’s robotics partners. Model tackles 200 tasks Google evaluated Gemini Robotics 2.5 across more than 200 distinct tasks, including serving food with tongs, tying bows on gift boxes, and transferring liquids with pipettes. These activities test a range of capabilities, from handling delicate objects to manipulating flexible materials and using everyday tools. Compared with previous baselines, the model achieved success rates that were 30 percent to 100 percent higher, depending on the task. It also completed activities 20 percent to 30 percent faster, according to Google. The model works across different robotic platforms, including Apptronik’s Apollo 2 humanoid and the Franka Duo system, which uses two-fingered parallel grippers. For the Mercedes-Benz demonstration, Google’s embodied reasoning model, Gemini Robotics ER, tracked the workflow, while Gemini Robotics 2.5 controlled the robot’s arms and hands. Apollo 2 picked metal brackets from supply bins and placed them into sequencing containers, adjusting its movements when necessary. Safety and training advances Beyond dexterity, Google has improved the model’s ability to navigate physical hazards. Its inference-time reasoning guidance helps robots avoid obstacles and operate around people. In company evaluations, the capability increased safe task completion by 33 percent around obstacles and 43 percent near people. Google also introduced ASIMOV-Jailbreak, an open-source benchmark designed to test whether robotic systems can resist disguised unsafe instructions. It contains hundreds of prompts spanning dozens of scenes. Google reported that Gemini 4 Argon achieved 99.5 percent resistance to these jailbreak attempts, compared with 82 percent for the previous Gemini Robotics ER 2 baseline. The company also credited Gemini 4 Argon with accelerating the development of its new robotics model. The system can generate thousands of simulated practice runs from real-world camera footage and create digital twins of physical environments. Researchers can combine these simulations with real training demonstrations to help robots generalize their skills to unfamiliar objects and settings. Argon can also analyze failed attempts and suggest improvements for subsequent training. The developments mark Google’s latest push to bring more adaptable robots into industrial and everyday environments. However, the 96 percent factory result remains a proof-of-concept, rather than evidence of widespread commercial deployment.Gemini Robotics 2.5 is currently being rolled out to Google’s robotics partners.Get the latest in engineering, tech, space & science - delivered daily to your inbox.With over a decade-long career in journalism, Neetika Walter has worked with The Economic Times, ANI, and Hindustan Times, covering politics, business, technology, and the clean energy sector. Passionate about contemporary culture, books, poetry, and storytelling, she brings depth and insight to her writing. When she isn’t chasing stories, she’s likely lost in a book or enjoying the company of her dogs.