At first I was like "What is this jerpint model that's beating the competition so soundly?" then it hit me, lol.
Anyhow this is like night and day compared to last year, and it's impressive that Sonnet is now apparently 50% as good as a professional human at this sort of thing.
I don't think comparing star counts would be a good measure though, as with AOC 90% of the effort and difficulty goes into the harder problems towards the end and it was the beginning, easy problems where the bulk of the sonnet's stars came from.
Anyhow this is like night and day compared to last year, and it's impressive that Sonnet is now apparently 50% as good as a professional human at this sort of thing.