umami · DeepSeek V4.1 Flash run 1
61.2Run score
Pass rate96.6%
Simplicity65.5
Problems $$2.05
DeepSeek V4.1 Flash uses the real production library (unagi-chan).
ImplementerPass rateSimplicityCostScore
DeepSeek V4.1 Flash · mini-SWE96.6%65.5$2.05
ProblemDeepSeek V4.1 Flash
Click a problem to see how each solution's score is built.