How Claude Performs on Robotics Tasks \ Anthropic
Do language models’ strengths transfer to robotics? Can a model perceive a scene, understand a particular robot’s state, and issue actions that reliably effect change in the physical world? We ran tests to find out.
Frontier Red Team Claude plays robotics Jul 9, 2026 Shmuel Berman, Michael Ilie, Jia Deng, and Daniel Freeman Do language models’ strengths transfer to robotics, a domain which requires the synthesis of logical skills and precise 3D understanding? Can a model perceive a scene, understand a particular robot’s state, and issue actions that reliably effect change in the physical world? We ran tests to find out. We gave several language models control over a range of robot bodies—including classic control toys, a simulated quadruped and humanoid, a robotic arm, and a real Unitree Go2 (the quadrupe
saved by
related reading
- Tracing the thoughts of a large language model \ Anthropicanthropic.com
- Robot-use agentsweb.mit.edu
- Project Fetch: Phase two \ Anthropicanthropic.com
- Project Fetch: Can Claude train a robot dog?anthropic.com
- GitHub - adam-maj/robotics: A deep dive on the history of robotics and the future of humanoidsgithub.com
- Emergence of Human to Robot Transfer in Vision-Language-Action Modelspi.website
- What work can robots do?anthropic.com
- State of Robot Learning, December 2025vedder.io
- A Unified Model for Motion-Conditioned Robot Co-designtransformer-transformer.github.io
- Stop Simulating, Start Experiencingpaoloai.substack.com
- Does Scaling Web-Video Pre-training Help Real Robots Do Real Work? | Rhoda AIrhoda.ai
- A VLA with Open-World Generalizationphysicalintelligence.company