Launching today
Gemini Robotics 2.5
Gemini Robotics 2.5: Google’s most capable robot model
1 follower
Gemini Robotics 2.5: Google’s most capable robot model
1 follower
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.
Launch tags:Artificial Intelligence
Launch Team
ClarifyThe Full-Stack AI CRM that replaces 5 tools
Promoted
Gemini Robotics 2.5 is Google DeepMind’s most capable vision-language-action (VLA) model to date. In plain terms, it turns what a robot sees and what it’s told into hand and arm movements, with the aim of teaching robots more skills, faster, in less structured real-world settings.
What’s new: a 30% to 100% higher success rate than previous baselines, depending on the task, and tasks completed 20% to 30% faster. It was evaluated across more than 200 tasks, including serving food with tongs, tying a bow on a gift box and pipetting liquid. It works with tool use, deformable objects like cloth and ribbon, and delicate items, and it runs across robot types, including Apptronik’s Apollo 2 humanoid and the Franka Duo two-arm platform.
Some results from DeepMind’s charts, comparing Gemini Robotics 2 with 2.5:
Packing pastries with tongs: 5% to 100%
Closing a toolbox lid: 0% to 93%
Untying ribbon bows: 0% to 70%
Hanging a cardigan: 0% to 62%
Folding pants: 0% to 40%
The real-world test: Apptronik’s Apollo 2 humanoids did automotive kitting (sorting parts from bulk bins into ordered trays) on active Mercedes-Benz production lines in Hungary and Germany, reaching a 96% success rate. DeepMind calls it “promising progress” toward industrial use, so it’s a pilot, not a finished deployment.
On safety, DeepMind added reasoning guidance at run time to steer robots around hazards, and reports 33% more safe task completion around obstacles and 43% around nearby people. It also released ASIMOV-Jailbreak, an open-source benchmark of prompts that disguise unsafe requests.
It isn’t something you can try yet. The post says Gemini Robotics 2.5 “is rolling out to our robotics partners”, and gives no API, pricing or regions. The comparisons are against DeepMind’s own earlier model, and the numbers are DeepMind’s.
Good fit if you work on robotics or embodied AI and want to see where general-purpose robot models are heading, especially for dexterous tasks and real production lines.
DeepMind’s announcement