umami · GLM 5.3 run 3

44.2Library score
Pass rate93.4%
Simplicity51.0
Problems $$10.63
Library $$24.06
The library
umami · designed by GLM 5.3 (mini-SWE)4,018 source lines
ImplementerPass rateSimplicityCostScore
DeepSeek V4.1 Flash · mini-SWE95.8%56.4$2.72
50.8
GLM 5.3 Flash · mini-SWE90.6%52.6$6.14
43.4
GPT-5.6 Luna · Codex93.8%44.1$1.76
38.3
ProblemDeepSeek V4.1 FlashGLM 5.3 FlashGPT-5.6 LunaMean

Click a problem to see how each solution's score is built.