Continual-ARCby unify

ReplayARC-AGI-1 · Fresh · GPT-6 Luna, high

Program library

Every answer is a program, kept once it reproduces the demonstrations and run first when the task returns.

Held-out tasks, budget used
18.6 solved 97%
Model spend
$0.77 420 calls
Instances
100 4 hours

Budget used is the share of the cap of 16 that an instance was charged, averaged over the instances: a solved instance costs 1 for each wrong answer and each demonstration, an unsolved one all 16, so lower is better.

Loading the run