AI learning to generate good conjectures will never show up as a benchmark being knocked down; it will show up as a shift in how mathematicians talk about the tools.

I think the way that you'd measure conjecture generating ability is going to be more subjective on like that tone shift where um it'll be mathematicians saying they're not just using it to like solve their problems, but as they step back and decide what their research field should even be that a conversation with such and such model like was genuinely helpful for that.