Operations Research Modeling and Solving on NEXTOR
76.31Accuracy (pass@1)NEDTree
Evaluation Results
| Method | Links | |
|---|---|---|
| NEDTreeType=Context-based2026.04 | 76.31 | |
| GPT-o4-miniType=Reasoning2026.04 | 52.63 | |
| ORllmAgentType=Prompt-based2026.04 | 52.63 | |
| Chain-of-ExpertsType=Prompt-based2026.04 | 51.32 | |
| Deepseek-R1Type=Reasoning2026.04 | 40.79 | |
| Deepseek-V3Type=Non-reasoning2026.04 | 26.31 | |
| GPT-4oType=Non-reasoning2026.04 | 18.42 | |
| OptimusType=Prompt-based2026.04 | 18.42 | |
| ORLM(best)Type=Fine-tuning2026.04 | 11.84 | |
| LLMOPTType=Fine-tuning2026.04 | 2.63 |