ARC-AGI-2 human baseline surpassed

(lesswrong.com)

9 points | by hugetim 3 days ago ago

2 comments

  • hugetim 3 days ago

    Contrary to what the leaderboard lists as the human score, their technical paper implies a human baseline of ~48%.

  • bskddkkddk 3 days ago

    [flagged]