List your company

Combinatorial Optimization on Crew Scheduling (test)

63.53Average PerformanceMCTS-AHD
30.270838.905447.5456.1746May 17, 2026

Evaluation results

MethodLinks
MCTS-AHDBudget=B=162026.0563.5386.21
MEMOIR (GPT-5-mini w/ GPT-5 critic)Budget=B=162026.0562.489.66
MEMOIR (GPT-5-mini)Budget=B=162026.0557.8375.86
GPT-5-miniBudget=B=162026.0557.3565.52
AIDEBudget=B=162026.055672.41
FunSearchBudget=B=162026.0555.6462.07
GreedyRefineBudget=B=162026.0555.4562.07
ReEvoBudget=B=162026.0552.7465.52
GPT-5 ChatBudget=B=162026.0551.6575.86
Classical SolverBudget=B=162026.0545.5—
o3-mini-highBudget=B=162026.0544.1265.52
MEMOIR (Qwen2.5-Coder-32B)Budget=B=162026.0531.5555