Assessing the CAD Capabilities of General-Purpose AI Models: A Case Study of GPT-6 Astra

A new empirical study assesses the CAD capabilities of general-purpose AI models, using GPT-6 Astra as its case study. The paper argues that recent advances in general-purpose models and agentic systems have enabled them to perform some CAD tasks, and that a systematic assessment is needed to establish what these systems can accomplish and how well their outputs meet engineering requirements.

Recent advances in general-purpose AI models and agentic systems have enabled them to perform some CAD tasks. A systematic assessment is now needed to establish what these systems can accomplish and how well their outputs meet engineering requirements. This paper presents an empirical study of GPT-6