P
umami · Production library run 1
46.4Library score
Pass rate92.8%
Simplicity53.9
Problems $$8.26
Implementers use the real production library (unagi-chan).
ImplementerPass rateSimplicityCostScore
DeepSeek V4.1 Flash · mini-SWE96.4%58.1$1.30
GLM 5.3 Flash · mini-SWE91.5%54.3$5.09
GPT-5.6 Luna · Codex90.4%49.4$1.87
ProblemDeepSeek V4.1 FlashGLM 5.3 FlashGPT-5.6 LunaMean
Click a problem to see how each solution's score is built.