CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design

arXiv 2026 39.9 method

TLDR

CADWorld is a benchmark for long-horizon computer-use agents in FreeCAD, spanning 200 tasks across 11 CAD workflow categories, where the strongest agent achieves 17.5% success versus 87% expert.

Reasoning

The paper introduces a well-motivated benchmark addressing a gap in agent evaluation for persistent engineering workflows. Strengths include realistic tasks, executable checks, and a clear performance gap; weaknesses include no new agent method and limited evidence outside benchmark results.

Read-first score

Read-first score 39.9, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 29.

Recency 8%

100

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

Methodology quality 25%

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

Reproducibility 25%

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

Topical relevance 42%

18.1

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

Frontier

Rank sensitivity

Stability: volatile; rank range: 42.

Keyword Scores

computer-aided design

parametric CAD

AI for CAD

CAD program

CAD generation

generative CAD

neural CAD

B-Rep

boundary representation

constructive solid geometry

CSG

sketch extrusion

CAD reconstruction

text-to-CAD

image-to-CAD

point cloud to CAD

Resources

Paper