Continual-ARC

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

Prime Agent, as shipped

Every learning mechanism the harness ships switched on.

Stream, budget used
27.7 solved 84%
Epilogue, budget used
25.3 solved 88%
Model spend
$9.99 3,932 calls
Instances
225 29.8 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.

Variant
Order

Loading the run