I’m guessing that 6-20 minutes is like the actual time spent driving screws or drilling holes. Each one takes maybe a few seconds. 6-20 minutes in that case translates to hundreds of screws driven, even on the low end. So not nearly as worthless as the time makes it sound.
Models are not improving? Since when? Last week? Newer models have been scoring higher and higher in both objective and subjective blind tests consistently. This sounds like the kind of delusional anti-AI shit that the OP was talking about. I mean, holy shit, to try to pass off “models aren’t improving” with a straight face.