MUSE Benchmark

What is MUSE?

MUSE evaluates text-to-CAD generation of complex B-Rep assemblies via design specifications. It scores models on code validity, geometric correctness, and…

Released

2026-05-27

Evaluates

CAD, General AI, Geometric reasoning, Science & Engineering

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2605.28579

MUSE paper

• Paper https://arxiv.org/abs/2605.28579
• Website https://dong7313.github.io/muse-benchmark/

Which sources cite MUSE?

• MUSE

Related CAD, General AI, Geometric reasoning, Science & Engineering benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench
• ActiveVision