Continual-ARC

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

Prime Agent, memory wiped

Everything the harness wrote deleted before every instance.

Stream, budget used
35.4 solved 73%
Epilogue, budget used
40.8 solved 60%
Model spend
$8.12 3,886 calls
Instances
225 22.7 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.

Variant
Effort
Order

Loading the run