Combinatorial Optimization on Resource Constrained Shortest Path (test)
84.47Average ScoreMEMOIR (Qwen2.5-Coder-32B)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MEMOIR (Qwen2.5-Coder-32B)Budget=B=162026.05 | 84.47 | 100 | |
| Classical SolverBudget=B=162026.05 | 75.09 | — | |
| Llama-3.3-70B-InstructBudget=B=162026.05 | 75.08 | 91.67 | |
| Qwen2.5-Coder-32BBudget=B=162026.05 | 75.08 | 91.67 | |
| GPT-5 ChatBudget=B=162026.05 | 75.08 | 91.67 | |
| o3-mini-highBudget=B=162026.05 | 75.08 | 91.67 | |
| DeepSeek-R1-Distill-Llama-70BBudget=B=162026.05 | 75.08 | 91.67 | |
| GPT-5-miniBudget=B=162026.05 | 75.08 | 91.67 | |
| AIDEBudget=B=162026.05 | 75.08 | 91.67 | |
| MCTS-AHDBudget=B=162026.05 | 75.08 | 91.67 | |
| ReEvoBudget=B=162026.05 | 75.08 | 91.67 | |
| MEMOIR (Llama-3.3-70B-Instruct)Budget=B=162026.05 | 75.08 | 91.67 | |
| MEMOIR (GPT-5-mini)Budget=B=162026.05 | 75.08 | 91.67 | |
| MEMOIR (GPT-5-mini w/ GPT-5 critic)Budget=B=162026.05 | 75.08 | 91.67 | |
| QwQ-32BBudget=B=162026.05 | 70.39 | 75 | |
| GreedyRefineBudget=B=162026.05 | 70.39 | 75 | |
| FunSearchBudget=B=162026.05 | 70.39 | 75 |