canon · GPT-6 Luna run 2
36.6Run score
Pass rate87.7%
Simplicity45.7
Problems $$0.08
GPT-6 Luna uses the real production library (pydantic).
ImplementerPass rateSimplicityCostScore
GPT-6 Luna · mini-SWE87.7%45.7$0.08
ProblemGPT-6 Luna
Click a problem to see how each solution's score is built.