Article

GPT-6 Astra Robot Manipulation Evaluation and LIBERO-GeoMotion Benchmark Released

The paper systematically evaluates GPT-6 Astra's closed-loop robot manipulation capabilities using a lightweight agent execution framework, finding a 26.92% success rate on RoboDojo and 76.0% on RoboTwin 2.0, but a clear gap between semantic reasoning and physical execution.

Part of the event: GPT-6 Astra Robot Manipulation Evaluation and New Benchmark Release

This page provides a summary and source link only.