Continual-ARC

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

Hermes Agent, memory wiped

Everything the harness wrote deleted before every instance.

Stream, budget used
39.0 solved 75%
Epilogue, budget used
38.3 solved 64%
Model spend
$15.34 33,564 calls
Instances
225 20.2 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