I tried LLM's for geolocation recently and it is both amazing how good they are at recognizing patterns and how terrible they are with recognizing and utilizing basic spatial relationships.
I've tried to use various OpenAI models for OpenSCAD code generation, and while the code was valid, it absolutely couldn't get spatial relationships right. Even in simple cases, like a U-tube assembled from 3 straight and 2 curved segments. So this is definitely an area for improvement.