Optimization Modeling on MAMO-C
74.88AccuracyDeepSeek-R1-0528
Evaluation results
| Method | Links | |
|---|---|---|
| DeepSeek-R1-0528Paradigm=Prompting-based, Solver=Gurobi2026.04 | 74.88 | |
| OpenAI o1Paradigm=Prompting-based, Solver=Gurobi2026.04 | 72.1 | |
| OptiMUSParadigm=Prompting-based, Solver=Gurobi2026.04 | 64.9 | |
| GPT-4o (CoE)Paradigm=Prompting-based, Solver=Gurobi2026.04 | 64 | |
| GPT-4o (CoT)Paradigm=Prompting-based, Solver=Gurobi2026.04 | 59.9 | |
| GPT-4o (Standard)Paradigm=Prompting-based, Solver=Gurobi2026.04 | 58.8 | |
| ORLM (SFT)Paradigm=Training-based, Base Model=Qwen2.5-7B, Solver=Gurobi2026.04 | 35.71 | |
| EVOM (GRPO)Paradigm=Training-based, Base Model=Qwen2.5-7B, Solver=Gurobi2026.04 | 34.28 | |
| Base ModelParadigm=Training-based, Base Model=Qwen2.5-7B, Solver=Gurobi2026.04 | 28.43 |