Operations Research Modeling and Solving on MAMO Easy
97Accuracy (pass@1)LLMOPT
Evaluation Results
| Method | Links | |
|---|---|---|
| LLMOPTType=Fine-tuning2026.04 | 97 | |
| NEDTreeType=Context-based2026.04 | 90.49 | |
| OptMATHType=Fine-tuning2026.04 | 89.9 | |
| GPT-o4-miniType=Reasoning2026.04 | 89.26 | |
| ORllmAgentType=Prompt-based2026.04 | 89.2 | |
| OptimusType=Prompt-based2026.04 | 89.11 | |
| Deepseek-V3Type=Non-reasoning2026.04 | 88.3 | |
| GPT-4oType=Non-reasoning2026.04 | 88.19 | |
| Chain-of-ExpertsType=Prompt-based2026.04 | 85.28 | |
| Deepseek-R1Type=Reasoning2026.04 | 82.97 | |
| ORLM(best)Type=Fine-tuning2026.04 | 82.3 |