ARC-AGI

A benchmark created by Francois Chollet that tests whether a system can solve novel reasoning tasks it was not trained on.

arcprize.org ↗

What people on korents have said about ARC-AGI, newest first — 1 position from 1 person.

1. 20 Dec 2024

   François Chollet archive

   Passing ARC-AGI does not amount to achieving AGI: o3 still fails on some very easy tasks, indicating fundamental differences from human intelligence.

   Passing ARC-AGI does not equate to achieving AGI, and, as a matter of fact, I don't think o3 is AGI yet. o3 still fails on some very easy tasks, indicating fundamental differences with human intelligence.

   ↗OpenAI o3 Breakthrough High Score on ARC-AGI-Pubarcprize.org