Continual-ARC

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

Demo-cache floor

The model alone, shown every demonstration it bought for the task again for free.

Stream, budget used
34.0 solved 64%
Epilogue, budget used
47.5 solved 48%
Model spend
$6.22 1,418 calls
Instances
225 30.5 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.

Effort
Order

Loading the run