Mathematical Optimization Modeling on Mamo complex
91AccuracyOR-LLM-Agent
Evaluation results
| Method | Links | ||
|---|---|---|---|
| OR-LLM-AgentModel=GPT-5.1, Method category=Prompt-based2026.05 | 91 | 81.8 | |
| TriVALModel=GPT-5.1, Method category=Prompt-based2026.05 | 90.5 | 86.9 | |
| TriVALModel=DeepSeek-V3.2, Method category=Prompt-based2026.05 | 90 | 88.8 | |
| OR-LLM-AgentModel=DeepSeek-V3.2, Method category=Prompt-based2026.05 | 88.6 | 76.8 | |
| OptiTreeModel=DeepSeek-V3.2, Method category=Prompt-based2026.05 | 82.9 | 71.2 | |
| OptiTreeModel=GPT-5.1, Method category=Prompt-based2026.05 | 80.5 | 74.1 | |
| AutoFormulationModel=DeepSeek-V3.2, Method category=Prompt-based2026.05 | 74.8 | 50.1 | |
| AutoFormulationModel=GPT-5.1, Method category=Prompt-based2026.05 | 74.3 | 52.1 | |
| SIRLMethod category=Learning-based2026.05 | 65.2 | 54.9 | |
| LLMOPTMethod category=Learning-based2026.05 | 50 | 31.9 | |
| ORLMMethod category=Learning-based2026.05 | 48.6 | 29.1 |