Continual-ARC

ReplayARC-AGI-2 · Fresh · GPT-6 Luna, max

Prime Agent, as shipped

Every learning mechanism the harness ships switched on.

Held-out tasks, budget used
33.3 solved 76%
Model spend
$1.58 642 calls
Instances
25 3.5 hours

Budget used is the share of the cap of 16 that an instance used, averaged over the instances: a wrong answer and a demonstration each cost 1, so lower is better.

Loading the run