The real turker studies, resulting in the ~70% number, are scored correctly I be...

		nmca on Dec 21, 2024 \| parent \| context \| favorite \| on: OpenAI O3 breakthrough high score on ARC-AGI-PUB The real turker studies, resulting in the ~70% number, are scored correctly I believe. Higher numbers are just speculated human performance as far as I’m aware.