Spectral Labs claims to have built the first AI system to achieve an industry standard CAD certification for mechanical engineers.
The company reports that its agent has passed the Solidworks Professional exam – autonomously building, modifying and assembling parts and mechanisms, completing the exam in less than three hours.
Founded in 2022, Spectral Labs has announced itself as a spatial intelligence company building foundation models for the next generation of engineering design.
Spectral Labs’ system combines SGS-Mk2, its foundation model for physical engineering, with Quartz, its CAD execution environment. SGS-Mk2 reasons about the geometry, topology, and kinematics of parts and assemblies.
On exam problems involving geometric reasoning, it claims that using SGS-Mk2 reduced per-problem costs by 46–to-87 per cent.
Spectral state that the CAD foundation model is lightweight and requires orchestration by a VLM. “It is a single set of weights which we condition and call through various tools within Quartz, each tool being defined according to the needs of a given problem stencil.
“We compared SGS-Mk2 with frontier models on 45 internally prepared CAD problems: 20 inspired by the CSWA and 25 by the CSWP. The CSWP problems covered all three segments: 10 for part modeling, 5 for part editing, and 10 for assemblies. A candidate counted as correct when its volume, center of mass, or distance was within 0.1% of the accepted value.”
No exam-specific training was undertaken, with the 45 emulated problems were prepared by its team internally. The exam has now been passed multiple times by the agent, but it is yet to achieve a perfect score. The test did however throw up a number of other interesting issues, both for the test itself and how other AI agents became stumped by exam exercises. You can read the full report here.
“There aren’t enough long-horizon benchmarks for CAD generation/editing/understanding,” said Spectral Labs CEO Rahul Iyer. “We put our model and system up against the Solidworks Professional Exam, a multi-hour and multi-task evaluation of CAD capabilities.
“Excited to share our results publicly, along with some of the research behind it. We’re actively growing the team and expanding our work with companies.”
The company says that it is expanding its work with manufacturers to automate engineering workflows end to end – from design and analysis through manufacturing and sourcing – with a focus on reducing development time and production costs.
