Google DeepMind · VLA Robotics Model

Gemini Robotics 2.5

Gemini Robotics 2.5 is Google DeepMind's vision-language-action model for robots, aimed at learning a wider range of skills faster. Across more than 200 tasks, it reports a 30% to 100% higher success rate than previous baselines, depending on task type, while completing tasks 20% to 30% faster. In a proof-of-concept with Apptronik's Apollo 2 humanoid on Mercedes-Benz production lines, it reached a 96% success rate on automotive kitting. The release also includes ASIMOV-Jailbreak, an open-source benchmark of prompts that disguise unsafe requests, and the model is rolling out to robotics partners.

Open the source ↗

Similar Agents & Automation releases

Learning Heterogeneous Tactile Representation for General Dexterous Manipulation
Bing Han, Yichuan Peng, Haoyu Dong, Yuanmeng Hu, Yongyi Jia, Fangjing Wang, Kecheng Zheng, Yiming Zhang (Robbyant) · Tactile Foundation Model · Week 47, 2026
World In-Context Learning for Agentic Robot Manipulation
Heng Fang, Zehui Guo, Yuehan Zhang, Mingyang Du, Dingkang Liang, Xiang Bai (H-EmbodVis) · In-Context Robot Learning · Week 47, 2026
NVIDIA Alpamayo 2 Edge and AlpaJudge
NVIDIA · Driving VLA model · Week 47, 2026
Toward the Era of Agentic Embodied Intelligence
Chao Liang, Ke Chen, Fengxiaoxiao Li, Shibo Huang, Yufeng Sun, Zhaokai Yin, Jianhuan Lai, Haozhe Feng (AutoLab) · Agentic Robot Control · Week 47, 2026
GR00T 2
NVIDIA · Open World Action Model · Week 47, 2026
FLEX
MIT and New York University researchers (led by Andreea Bobu, MIT) · LLM Robot Planning · Week 47, 2026

Gemini Robotics 2.5

Similar Agents & Automation releases

More from Google DeepMind