Awesome AI4CAD Hub Papers · Datasets · Projects
← Back to papers

Text-to-CAD Evaluation with CADTests

arXiv 2026 59.7 method

TLDR

Introduces CADTestBench, a test-based benchmark for evaluating Text-to-CAD models using executable software tests.

Reasoning

The paper addresses a critical gap in Text-to-CAD evaluation with a novel automated testing approach. Its strengths include a practical benchmark and demonstrated utility for guiding generation, though the abstract lacks details on real-world deployment or limitations of the tests.

Read-first score

Read-first score 59.7, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 63.

Recency 8%
100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 25%
90

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=baseline,benchmark,dataset,evaluation,metric

Reproducibility 25%
50

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=code,dataset,github

Topical relevance 42%
39.4

Uses existing LLM keyword relevance scores normalized to 0-100. AI for CAD,computer-aided design,neural CAD,generative CAD,parametric CAD,B-Rep,boundary representation,constructive solid geometry,CSG,sketch extrusion,CAD generation,CAD reconstruction,text-to-CAD,image-to-CAD,point cloud to CAD,CAD program

Field roles

FrontierBridgeMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 20.

Keyword Scores

text-to-CAD
10
CAD generation
9
computer-aided design
8
generative CAD
8
AI for CAD
7
neural CAD
5
parametric CAD
4
CAD program
3
CAD reconstruction
2
B-Rep
1
boundary representation
1
constructive solid geometry
1
CSG
1
sketch extrusion
1
image-to-CAD
1
point cloud to CAD
1

Deep Analysis

Innovations

  • New evaluation perspective for Text-to-CAD based on automated testing
  • CADTestBench: the first test-based benchmark for Text-to-CAD
  • CADTests: executable software tests that verify geometric and topological requirements of generated CAD models
  • Using CADTests to guide CAD model generation, yielding simple baselines that surpass current methods

Methodology

The paper introduces CADTestBench, a benchmark that uses CADTests (executable software tests) to evaluate Text-to-CAD models by checking whether generated CAD models satisfy the geometric and topological constraints from input prompts. They benchmark recent methods and also employ CADTests to guide generation, creating simple baselines that outperform existing approaches.

Key Results

Comprehensive benchmarking of recent Text-to-CAD methods is conducted; simple baselines guided by CADTests surpass the performance of current methods.

Tags

CVAILGRO