# BenchCAD: A Comprehensive, Industry-Standard Benchmark for Programmatic CAD

arXiv: https://arxiv.org/abs/2605.10865 · HTML: https://mlsanity.com/paper/2605.10865/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 11 May 2026.

## Builds on (most cited first, 7 of 7)

- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [DeepCAD: A Deep Generative Network for Computer-Aided Design Models](https://mlsanity.com/paper/2105.09492/) (2021)
- [Croissant: A Metadata Format for ML-Ready Datasets](https://mlsanity.com/paper/2403.19546/) (2024)
- [CAD-Recode: Reverse Engineering CAD Code from Point Clouds](https://mlsanity.com/paper/2412.14042/) (2024)
- [CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward](https://mlsanity.com/paper/2505.19713/) (2025)
- [Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Prompts](https://mlsanity.com/paper/2409.17106/) (2024)
- [CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing](https://mlsanity.com/paper/2502.03997/) (2025)

## Built on by (most cited first, 15 of 15)

- [P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning](https://mlsanity.com/paper/2606.11152/) (2026)
- [CADENA: Stepwise CAD Reverse Engineering](https://mlsanity.com/paper/2608.00799/) (2026)
- [3DHarnessBench: Probing Agentic 3D-to-Code Capabilities of Frontier Vision-Language Models](https://mlsanity.com/paper/2609.06535/) (2026)
- [CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design](https://mlsanity.com/paper/2609.16251/) (2026)
- [Prompting Image Generators for Training-free Primitive Shape Abstraction](https://mlsanity.com/paper/2607.05568/) (2026)
- [An Exam for Active Observers](https://mlsanity.com/paper/2607.16165/) (2026)
- [RealCADBench: Benchmarking Parametric CAD Modeling from Industrial Design Intents](https://mlsanity.com/paper/2609.03773/) (2026)
- [VisCAD: A Foundation Model Suite with Multimodal Industrial CAD Intelligence](https://mlsanity.com/paper/2609.03811/) (2026)
- [DepthBenchCAD: When Does Deeper Auditing Yield More Reliable Conclusions?](https://mlsanity.com/paper/2609.15122/) (2026)
- [MechReason: Benchmarking Multi-Image Multi-Hop Reasoning in Mechanical Engineering](https://mlsanity.com/paper/2609.16012/) (2026)
- [2d-fet-bench: from spatial reasoning to fet design on flakes](https://mlsanity.com/paper/2610.07423/) (2026)
- [CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use](https://mlsanity.com/paper/2610.09127/) (2026)
- [BrickBench: Evaluating Agentic Brick Design](https://mlsanity.com/paper/2610.12452/) (2026)
- [Mind the Spatial Gap: A Benchmark for Geospatial Reasoning and Constrained Spatial Editing](https://mlsanity.com/paper/2610.12881/) (2026)
- [ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling](https://mlsanity.com/paper/2610.15166/) (2026)

## Abstract (arXiv)

Industrial Computer-Aided Design (CAD) code generation requires models to produce executable parametric programs from visual or textual inputs. Beyond recognizing the outer shape of a part, this task involves understanding its 3D structure, inferring engineering parameters, and choosing CAD operations that reflect how the part would be designed and manufactured. Despite the promise of Multimodal large language models (MLLMs) for this task, they are rarely evaluated on whether these capabilities jointly hold in realistic industrial CAD settings. We present BenchCAD, a unified benchmark for industrial CAD reasoning. BenchCAD contains 17,900 execution-verified CadQuery programs across 106 industrial part families, including bevel gears, compression springs, twist drills, and other reusable engineering designs. It evaluates models through visual question answering, code question answering, image-to-code generation, and instruction-guided code editing, enabling fine-grained analysis across perception, parametric abstraction, and executable program synthesis. Across 10+ frontier models, BenchCAD shows that current systems often recover coarse outer geometry but fail to produce faithful parametric CAD programs. Common failures include missing fine 3D structure, misinterpreting industrial design parameters, and replacing essential operations such as sweeps, lofts, and twist-extrudes with simpler sketch-and-extrude patterns. Fine-tuning and reinforcement learning improve in-distribution performance, but generalization to unseen part families remains limited. These results position BenchCAD as a benchmark for measuring and improving the industrial readiness of multimodal CAD automation.