Serious answer: no model ever gets close to writing an architectural floor plan that makes sense.

They understand all the rules and best practices, they can (sometimes) spot a bad idea in a floor plan, they can describe a good floor plan.

But ask them to make one, even if you give it every detail (even a "node graph" of rooms), they will still output nonsense. Same for text and image models.

Floor plans should be the new Pelican Benchmark.

10000% , imho opinion core issue is that cd-level architectural plan-sets en masse are overly shielded by design firms and clients. Diffusion/AI vision has a data problem in this regard.

Also, LLMs fundamentally lacks a spatial intuition or comprehension of orthographic /sectional drawings.

Could it write a deterministic constraint solving program that at least gives it a head start at narrowing down options?

I had this experience too. I had blueprints from the builder and wanted a 'nice' floor rendering like some apartments have. I fed it the blueprints and let it iterate. Even giving it plenty of time, dimensions, etc. it just couldn't create something that matched reality.