Assessing the CAD Capabilities of General-Purpose AI Models: A Case Study of GPT-6 Astra
Abstract
GPT-6 Astra demonstrates partial capability across CAD workflows but remains limited by geometric validity, parametric dependencies, and assembly errors.
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 Astra, a SOTA general-purpose AI model, across four basic CAD tasks: model understanding, generation, editing, and evaluation. We design test cases spanning different levels of complexity and engineering requirements. The results show that GPT-6 Astra can support multiple stages of CAD workflows, with successful outcomes in cases involving nontrivial geometric complexity. This suggests that general-purpose AI is beginning to offer practical value in almost all steps in CAD workflow. However, gaps remain between generating visually plausible geometry and producing valid, functional, and editable CAD models. Recurring errors in freeform geometry, parameter dependencies, and mating relationships between parts limit engineering usefulness. Agentic iterative refinement can improve results but does not consistently resolve critical errors; long completion times further constrain practical use.
Community
Can frontier AI models generate CAD models that are actually usable in engineering?
Unlike evaluations centered on simplified or toy examples, our study assesses GPT-6 Astra using realistic engineering CAD models with nontrivial complexity. More importantly, we evaluate not only whether AI can generate CAD geometry, but also whether the resulting models satisfy multiple engineering usability requirements, including geometric validity, functional completeness, assembly feasibility, and parametric editability.
Across CAD understanding, generation, editing, and evaluation tasks, our findings reveal an important transition: general-purpose AI models are beginning to demonstrate practical value in engineering design, while significant challenges remain in ensuring engineering reliability.
The key question is no longer just whether AI can create CAD models, but whether those models can actually be used in engineering workflows.
Paper: https://arxiv.org/abs/2610.24451
Project: https://qiang-zou.github.io/projects/icad-eval-report/
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper