← News
Release

gNucleus AI publishes Parametric CAD Bench v3 for AI agents that author parametric CAD

gNucleus AI

Benchmark cadbench.ai⁠Paper arxiv.org⁠

gNucleus AI publishes the paper for Parametric CAD Bench v3, which grades AI agents on parametric design intent, modelling-history preservation and feature-level editability, not only on whether a generated 3D model looks right. It has 100 real-world-inspired tasks in three workflows: text-to-CAD creation, text-to-CAD create-and-edit, and image-to-CAD from engineering drawings. The paper reports a snapshot of 13 model-agent systems as of 24 September 2026; according to a company author, Claude Code with Opus 5.5 leads with an overall 61.03% and 84.66% on image-to-CAD. The benchmark, leaderboard and trajectories were released in September.

Share on LinkedIn, X or Bluesky, or .

Know related work that belongs here?

Something wrong on this page?

More news

All news
  1. ReleaseUniversalAGI releases SUV-PT, an SUV aerodynamics model with 1.1% drag error on DrivAerML
  2. EventAutoCFD5 uses DrivAerML as the common training set for its AI/ML comparison of road-car surrogates
  3. ReleaseLuminary's SHIFT-NVH predicts road-induced body vibration from part gauges, material and speed
  4. ReleaseXplore's RWE-Bench grades AI agents with physics solvers on CAD, PCB and CFD tasks