arXiv:2611.02659 · Submitted November 2, 2026
Parametric CAD Bench v3: Evaluating Agentic Parametric CAD Authoring from Text and Engineering Drawings
Mei Chen, Yu Xia, Haipeng Mao
A benchmark of 100 FreeCAD tasks covering creation from text, create-and-edit workflows, and reconstruction from engineering drawings. The paper describes the evaluation protocol and a September 24, 2026 snapshot of 13 model-agent systems, with native CAD artifacts assessed by a separate verifier.