What would you consider such evidence to look like?

For one, these models should be able to understand the physical world via images, audio, and video. I do agree that current models are quite good at coding, but that's mainly because coding is entirely text-based and easily verifiable. It's not obvious that this capability will transfer to other domains that aren't text-based and aren't as easily verifiable.

Well for starters the calendar year would have to be 2027 CE at the very earliest.