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)→
More from Research
- Churchland lab builds RNN implementation of GLM-HMM to model engagement fluctuations — anne_churchland · 2026-11-19
- Energy-Based Reasoners: 1.8M-param model hits 99.9% on Sudoku-Extreme with 345x less inference compute — LucaAmb · 2026-11-19
- New MAC Bench finds frontier agents coordinate poorly: 8-agent teams win by exploration, not teamwork — AlexGDimakis · 2026-11-19
- LLNL releases SciResearch-Eval, a benchmark testing AI scientific judgment with broken simulators — alex_verem · 2026-11-19
- LLNL benchmark: only 2 of 9 AI models stay accurate when the simulator is secretly wrong — alex_verem · 2026-11-19
- HiT image generator learns its own abstraction hierarchy, hits 1.48 FID on ImageNet 256 — LucaAmb · 2026-11-19