Continual-ARC

ReplayARC-AGI-1 · Workstreams · GPT-6 Luna, low

Demo-cache floor

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

Stream, budget used
38.1 solved 63%
Epilogue, budget used
47.8 solved 48%
Model spend
$1.60 1,548 calls
Instances
225 5.5 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