Skip to content

Dataset · gnucleus-ai

Parametric CAD Benchmark Results Dataset

gnucleus-ai/cad-gen-freecad-bench

Test results of AI agents creating editable FreeCAD models from text descriptions.

What's inside

The dataset contains line-by-line results of the Parametric CAD Bench (1,000 rows in parquet format), measuring the ability of AI agents to create editable FreeCAD models based on text descriptions. Each row reflects the metrics of a specific agent, model, and task.

What you can do with it

  • Evaluating and comparing AI agents in CAD model generation tasks
  • Analyzing automatic design quality based on text descriptions
Size
1K–10K rows
Downloads this month
20.9K
Likes
2

How to load it

from datasets import load_dataset

ds = load_dataset("gnucleus-ai/cad-gen-freecad-bench")