OpenAI · GPT · Claude · Crypto Briefing
Astra agent performs zero-shot robot control with 95% success rate in real-world tests
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
OpenAI's GPT-6 Astra demonstrated zero-shot pick-and-place tasks on a full humanoid robot, building on a 95% success rate achieved with dual robotic arms.
Key facts
- Astra hit a 98% success rate, nailing 49 out of 50 single-arm assignments in RoboLab benchmarks
- In evaluations conducted by third-party organization RoboCurve, Astra achieved a 95% success rate on a physical pick-and-place task, successfully completing 19 out of 20 attempts using dual bimanual
- OpenAI's GPT-6 Astra demonstrated zero-shot pick-and-place tasks on a full humanoid robot, building on a 95% success rate achieved with dual robotic arms
- Each run consumed roughly 2.1k tokens of output and finished in approximately 2.5 minutes
Summary
OpenAI’s GPT-6 Astra has crossed a threshold that robotics researchers have been chasing for years: controlling a full humanoid robot to perform pick-and-place tasks without any task-specific training. In evaluations conducted by third-party organization RoboCurve, Astra achieved a 95% success rate on a physical pick-and-place task, successfully completing 19 out of 20 attempts using dual bimanual robot arms known as the I2RT YAM. Each run consumed roughly 2.1k tokens of output and finished in approximately 2.5 minutes. In simulation environments, the numbers got even better.