Continual-ARC

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

Prime Agent, memory wiped

Everything the harness wrote deleted before every instance.

Stream, budget used
30.8 solved 80%
Epilogue, budget used
28.3 solved 88%
Model spend
$10.45 3,874 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.

Variant
Order

Loading the run