The AI arena is free today

Open Superagent
All benchmarks

CADGenBench

Implementation

Progress Over Time

Interactive timeline showing model performance evolution on CADGenBench

State-of-the-art frontier
Open
Proprietary

CADGenBench Leaderboard

1 models
ContextCostLicense
1
xAI
Grok 4.7
xAI
—500K$2.00 / $6.00
Notice missing or incorrect data?
About this benchmark

What is CADGenBench?

CADGenBench evaluates agents on CAD model construction from design prompts. The generation split requires producing CAD geometry graded for executability and geometric correctness. Distinct from BenchCAD.

CADGenBench is a text benchmark evaluating models on engineering, agents, and code tasks. LLM Stats tracks 1 models on this benchmark, scored on a 0–1 scale. The current average is 0.4, with the leader at 0.4.

Compare leaders on the best AI for engineering, best AI for agents and best AI for code leaderboards.

Current leaders

Grok 4.7 from xAI currently leads the CADGenBench leaderboard with a score of 0.444 across 1 evaluated AI models.

1Grok 4.7xAI44.4%

FAQ

Common questions about the CADGenBench benchmark and leaderboard.

What is the CADGenBench benchmark?

CADGenBench evaluates agents on CAD model construction from design prompts. The generation split requires producing CAD geometry graded for executability and geometric correctness. Distinct from BenchCAD.

What is the CADGenBench leaderboard?

The CADGenBench leaderboard ranks 1 AI models based on their performance on this benchmark. Currently, Grok 4.7 by xAI leads with a score of 0.444. The average score across all models is 0.444.

What is the highest CADGenBench score?

The highest CADGenBench score is 0.444, achieved by Grok 4.7 from xAI.

How many models are evaluated on CADGenBench?

1 models have been evaluated on the CADGenBench benchmark, with 0 verified results and 1 self-reported results.

Where can I find the CADGenBench dataset?

The CADGenBench dataset is available at https://www.mecado.com/.

What categories does CADGenBench cover?

CADGenBench is categorized under engineering, agents, and code. The benchmark evaluates text models.

Which model offers the best value on CADGenBench?

Among models scoring within 10% of the leader, Grok 4.7 from xAI is the cheapest, at $2.00 per million input tokens with a score of 0.444.

How recent are the CADGenBench leaderboard results?

The CADGenBench leaderboard was last updated in October 2026 and currently includes 1 evaluated models.