Top solve rate is currently 24% with Opus 4.8... What's a competent human supposed to score?
presumably whatever the top model uses and then some, since the human can use the model.
I wonder if a model could score higher if it had a human at its disposal?
alt Hacker News
presumably whatever the top model uses and then some, since the human can use the model.
I wonder if a model could score higher if it had a human at its disposal?