Optimization Modeling on IndustryOR (Accuracy, Run Time)
63.7AccuracySAC-Opt
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SAC-Opt2025.09 | 63.7 | 79 | |
| Best-baseline2025.09 | 54 | 113.08 | |
| StarORMethod Category=Test-Time Methods, Base model=Qwen3-4B-Instruct-25072026.06 | 51 | — | |
| DeepSeek-R1Method Category=Model-based Methods2026.06 | 45 | — | |
| DeepSeek-V3.1Method Category=Model-based Methods2026.06 | 44 | — | |
| OpenAI-o3Method Category=Model-based Methods2026.06 | 44 | — | |
| Best-of-NMethod Category=Test-Time Methods, Base model=Qwen3-4B-Instruct-2507, N=162026.06 | 39 | — | |
| ORLM-LLaMA3-8BMethod Category=Learning-based Methods2026.06 | 38 | — | |
| OR-R1-Qwen3-8BMethod Category=Test-Time Methods, Base model=Qwen3-4B-Instruct-25072026.06 | 35.3 | — | |
| GPT-4Method Category=Model-based Methods2026.06 | 33 | — | |
| SIRL-Qwen2.5-7BMethod Category=Learning-based Methods2026.06 | 33 | — | |
| OptiTreeMethod Category=Test-Time Methods, Base model=Qwen3-4B-Instruct-25072026.06 | 33 | — | |
| AutoFormulatorMethod Category=Test-Time Methods, Base model=Qwen3-4B-Instruct-25072026.06 | 30 | — | |
| LLMOPT-Qwen2.5-14BMethod Category=Learning-based Methods2026.06 | 29 | — | |
| ReflexionMethod Category=Test-Time Methods, Base model=Qwen3-4B-Instruct-25072026.06 | 28 | — | |
| Zero-shotMethod Category=Test-Time Methods, Base model=Qwen3-4B-Instruct-25072026.06 | 27 | — | |
| OptMATH-Qwen2.5-7BMethod Category=Learning-based Methods2026.06 | 20 | — |