Gemini Robotics 2.5

Google has launched Gemini Robotics 2.5, its most capable vision-language-action model to date, delivering gains in dexterity, reliability and safety across more than 200 tested tasks. In a real-world proof of concept on a Mercedes-Benz production line, it drove Apptronik's Apollo 2 humanoid to pick and pack auto parts with a 96% success rate, improving success by 30-100% and speed by 20-30% over prior baselines. The model is now opening to Google's robotics partners.

Google DeepMind unveiled Gemini Robotics 2.5, a vision-language-action model it says outperforms its own prior baselines by 30 to 100 percent depending on task type. On active Mercedes-Benz production lines in Hungary and Germany, Apptronik's humanoid Apollo 2 sorted metal parts with a reported 96 percent success rate. DeepMind also uses Gemini 4 Argon as a simulation engine for training and open-sourced the ASIMOV-Jailbreak benchmark to test robotics model safety.

Google DeepMind has released Gemini Robotics 2.5, a vision-language-action model with substantially improved dexterous manipulation that has already performed real work in Mercedes-Benz factories and enables Apptronik's Apollo 2 humanoid to tie a bow with five-fingered hands. The team also introduced ASIMOV-jailbreak, an open safety benchmark aimed at evaluating robots operating alongside humans.

Google DeepMind unveiled Gemini Robotics 2.5, its most capable vision-language-action (VLA) model to date, expanding both the breadth of skills robots can learn and the speed at which they acquire them. The release boosts dexterity, reliability and safety so robots can move beyond the lab into unstructured real-world environments, aided by Gemini 4 Argon and partners including Agile, Apptronik and Mercedes-Benz.