Continual-ARC

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

Program library

Every answer is a program, kept once it reproduces the demonstrations and run first when the task returns.

Stream, budget used
8.0 solved 96%
Epilogue, budget used
26.5 solved 80%
Model spend
$6.16 462 calls
Instances
225 30.2 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.

Order

Loading the run