We introduce neuralCAD-Edit, the first benchmark for editing 3D CAD models collected from expert CAD engineers. Instead of text conditioning as in prior works, we collect realistic CAD editing requests by capturing videos of professional designers, interacting directly with CAD models in CAD software, while talking, pointing and drawing. We recruited ten consenting designers to contribute to this contained study. We benchmark leading foundation models against human CAD experts carrying out edits, and find a large performance gap in both automatic metrics and human evaluations. Even the best foundation model (GPT 5.2) scores 53% lower (absolute) than CAD experts in human acceptance trials, demonstrating the challenge of neuralCAD-Edit. We hope neuralCAD-Edit will provide a solid foundation against which 3D CAD editing approaches and foundation models can be developed. Code/data: https://autodeskailab.github.io/neuralCAD-Edit

翻译：我们提出神经CAD编辑（neuralCAD-Edit），这是首个由CAD工程师专家采集的三维CAD模型编辑基准。与以往基于文本条件的方法不同，我们通过录制专业设计师在CAD软件中直接交互操作CAD模型时的讲解、指向与绘图过程，收集了真实的CAD编辑需求。我们招募了十名知情同意的设计师参与这项限定研究。我们对比了领先的基础模型与人类CAD专家执行编辑任务的表现，发现两者在自动评估指标和人工评价中均存在显著性能差距。即使用户验收测试中表现最佳的基础模型（GPT 5.2），其评分仍比CAD专家低53%（绝对值），这凸显了神经CAD编辑的挑战性。我们期望该基准能为三维CAD编辑方法及基础模型的研发提供坚实基础。代码/数据见：https://autodeskailab.github.io/neuralCAD-Edit