Continual-ARC

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

Hermes Agent, memory wiped

Everything the harness wrote deleted before every instance.

Stream, budget used
41.1 solved 73%
Epilogue, budget used
49.5 solved 48%
Model spend
$15.34 35,200 calls
Instances
225 18.6 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