P
simu · Production library run 1
44.8Library score
Pass rate90.9%
Simplicity57.1
Problems $$5.62
Implementers use the real production library (simpy).
ImplementerPass rateSimplicityCostScore
DeepSeek V4.1 Flash · mini-SWE91.5%59.8$1.21
GLM 5.3 Flash · mini-SWE92.3%58.6$2.97
GPT-5.6 Luna · Codex89.1%53.2$1.44
ProblemDeepSeek V4.1 FlashGLM 5.3 FlashGPT-5.6 LunaMean
intermodal-terminal-flow38.236.738.737.8diagnostic-specimen-release45.20.052.932.7rail-corridor-recovery91.094.377.987.7binary-offload-episode56.369.055.560.3packet-schedulers42.858.032.744.5wildfire-relief-depot66.40.068.745.0preempted-fault-race72.378.744.365.1rendezvous-rollback67.444.315.242.3filter-reservation31.130.435.132.2one-shot-bell60.837.538.545.6quorum-poisoned-losers46.353.946.949.0harbor-surge23.715.319.019.3harbor-vessels25.10.038.421.2