Operations Research Modeling and Solving on OptMATH
45.18Accuracy (pass@1)GPT-o4-mini
Evaluation results
| Method | Links | |
|---|---|---|
| GPT-o4-miniType=Reasoning2026.04 | 45.18 | |
| ORllmAgentType=Prompt-based2026.04 | 45.18 | |
| NEDTreeType=Context-based2026.04 | 42.16 | |
| Deepseek-R1Type=Reasoning2026.04 | 40.96 | |
| LLMOPTType=Fine-tuning2026.04 | 40 | |
| Chain-of-ExpertsType=Prompt-based2026.04 | 39.7 | |
| GPT-4oType=Non-reasoning2026.04 | 34.94 | |
| OptMATHType=Fine-tuning2026.04 | 34.7 | |
| Deepseek-V3Type=Non-reasoning2026.04 | 32.6 | |
| OptimusType=Prompt-based2026.04 | 19.28 | |
| ORLM(best)Type=Fine-tuning2026.04 | 9.03 |