CAD Arena B

Name: CAD Arena
Creator: Normal
Keywords: Chip Design

AI benchmark · Chip Design

Publisher: Normal
Domains: Chip Design
On X: @normalfactoryco ↗
Tier: B why
Snapshot: October 11, 2026

Open benchmark ↗normal.ai/research/cadarena

Latest from Normal on X

@normalfactoryco ↗

We investigated a seemingly simple question: how do you grade if AI generated parts or assemblies are correct? Here's how we improved on this with our verifier, FrontierCAD.
— normalfactoryco (@normalfactoryco) Oct 5, 2026
Opus 5.5 is the new #1 on CADArena. We added six new models. Opus 5.5 scores 0.750 and takes the top spot from GPT-6 Astra (0.671). And Grok 4.7 scores below Grok 4.6 and GPT-6 Luna.
— normalfactoryco (@normalfactoryco) Sep 25, 2026
The world around you is designed in CAD. How well can AI build it? Introducing CADArena, benchmarking AI CAD generation across the tools engineers use Agents can now build accurate geometry, but struggle to create feature trees engineers can maintain and edit
— normalfactoryco (@normalfactoryco) Sep 9, 2026

What is CAD Arena?

CAD Arena measures how well AI agents reconstruct real manufactured parts from engineering drawings as editable CAD models with usable feature trees across platforms like NX, SolidWorks, Onshape, Fusion and Build123d.

Robotics mostly
“CAD Arena tests how agents turn drawings into editable parts across the tools used to build the manufactured world.”
normal.ai/research/cadarena ↗
Coding
“The agent constructs the part through the selected CAD platform’s scripting language or API, using tool feedback to revise the part.”
normal.ai/research/cadarena ↗

Who built CAD Arena

Normal built it
“We introduce CAD Arena, an evaluation of how well AI agents reconstruct real parts as CAD models with human usable feature trees.”
normal.ai/research/cadarena ↗

Tier B

Established: 15 or more models scored, or curated RL directories rate it.

How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.

built by Normal
in curated RL directories (3 pts)

How we got to tier B

Adoption: built by Normal. Tier C.
Not yet read on X.
In curated RL directories: 3 points, a floor of B. Raised to B.
Confirmed: a line from its own site or paper places it.

A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.

Where CAD Arena sits

Its realm in the universe, live. Hover a star for its name; click to open it. Open it in the universe

The galaxy could not load. See every vendor on the board.

Chip Design RL environments

Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-10-11 snapshot.