Continual-ARC

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

Prime Agent, as shipped

Every learning mechanism the harness ships switched on.

Stream, budget used
42.8 solved 71%
Epilogue, budget used
46.3 solved 56%
Model spend
$1.77 2,737 calls
Instances
225 3.3 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