I tried o3, instant-5.3, Opus 3, and haiku 4.5, and couldn't get them to give bad answers to the couch: stairs vs elevator question. Is there a specific wording you used?
Well if it's one of those hospital elevators that can take a bed with a patient, you probably could. Or if it's a small 2 seater sofa. The question isn't as dumb as it sounds at first, and a human would definitely ask a follow up question.