Continual-ARC

ReplayARC-AGI-1 · Random · GPT-6 Luna, medium

Stateless floor

The model alone, with nothing kept between instances.

Stream, budget used
32.6 solved 81%
Epilogue, budget used
27.0 solved 84%
Model spend
$1.95 1,334 calls
Instances
225 9 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