Continual-ARC

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

OpenClaw, told to keep a program library

Told to keep one tested program per task and run it first when the task returns.

Stream, budget used
26.3 solved 84%
Epilogue, budget used
36.3 solved 84%
Model spend
$59.42 10,125 calls
Instances
225 20.9 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.

Loading the run