Text2CAD-Bench: A Benchmark for LLM-based Text-to-Parametric CAD Generation

TL;DR

Text2CAD-Bench is a comprehensive benchmark for evaluating large language models' ability to generate parametric CAD models from natural language across varying complexity levels.

Contribution

It introduces the first systematic benchmark covering geometric complexity and application diversity for text-to-CAD generation.

Findings

Models perform well on basic geometry but struggle with complex topology.

Benchmark includes 600 examples across four complexity levels.

Current models' performance degrades significantly on advanced features.

Abstract

Text-to-CAD generation aims to create parametric CAD models from natural language, enabling rapid prototyping and intuitive design workflows. However, existing benchmarks focus on basic primitives and simple sketch-extrude sequences, lacking advanced features essential for real-world applications and covering only traditional mechanical parts. We introduce Text2CAD-Bench, the first benchmark systematically evaluating text-to-CAD across geometric complexity and application diversity. Our benchmark comprises 600 human-curated examples spanning four levels: L1-L2 cover fundamental geometry with standard features, L3 introduces complex topology and freeform surfaces, and L4 extends to real-world domains beyond mechanical parts. Each example pairs dual-style prompts -- geometric descriptions mimicking non-expert users, and procedural sequences aligned with expert-level conventions. Evaluating mainstream general LLMs and domain-specific models, we find that current models perform reasonably on basic geometry but degrade substantially on complex topology and advanced features. We release our benchmark to drive progress in text-to-CAD research.