SolidWorks-Bench: No model can assemble a machine; Fable 5.2 leads at 57%

DevvMandal · x · 2026-11-19

A new benchmark, SolidWorks-Bench, tests whether AI models can perform real mechanical engineering tasks inside SolidWorks. Results show models get close on individual parts but struggle to assemble them — no model completes a single machine. Fable 5.2 leads with a 57% mean reward. The team is also booking calls about its engineering/CUA datasets and environments.

Related event: SolidWorks-Bench: No AI Model Can Assemble a Full Machine(3 posts)→

Original post →

More from Research

Research channel →