Continual-ARC

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

Stateless floor

The model alone, with nothing kept between instances.

Stream, budget used
46.2 solved 50%
Epilogue, budget used
47.8 solved 52%
Model spend
$6.86 1,781 calls
Instances
225 32.9 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.

Effort
Order

Loading the run