plaid · DeepSeek V4 Flash run 3
33.8Run score
Pass rate94.9%
Simplicity43.5
Problems $$6.78
DeepSeek V4 Flash uses the real production library (megaparsec).
ImplementerPass rateSimplicityCostScore
DeepSeek V4 Flash · mini-SWE94.9%43.5$6.78
ProblemDeepSeek V4 Flash
Click a problem to see how each solution's score is built.