Gemini Robotics 2.5 is Google DeepMind’s most capable vision-language-action model, turning what a robot sees and is told into hand and arm movements. Per DeepMind, it has a 30% to 100% higher success rate than the previous baseline, finishes tasks 20% to 30% faster, and reached 96% success in a Mercedes-Benz parts-kitting pilot with Apptronik’s Apollo 2 humanoid. Works across robot types. Rolling out to robotics partners.