Optimization Modeling on NLP4LP
94AccuracySAC-Opt
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SAC-Opt2025.09 | 94 | 73.97 | |
| SAC-OptBackbone=GPT-4o, Number of runs=52025.09 | 94 | — | |
| SAC-Opt2025.09 | 94 | — | |
| Best-baseline2025.09 | 89.8 | 71.86 | |
| OptiMUS-0.3Backbone=GPT-4o, Number of runs=52025.09 | 89.8 | — | |
| OptiMUSversion=0.32025.09 | 89.8 | — | |
| CoEreferenced=true2025.09 | 87.4 | — | |
| OptiMUS-0.2Backbone=GPT-4o, Number of runs=52025.09 | 86.5 | — | |
| OptiMUSversion=0.22025.09 | 86.5 | — | |
| ReflexionBackbone=GPT-4o, Number of runs=52025.09 | 82.4 | — | |
| Reflexion2025.09 | 82.4 | — | |
| CoTreferenced=true2025.09 | 74.7 | — | |
| Standardreferenced=true2025.09 | 73.6 | — | |
| CAFAreferenced=true2025.09 | 50 | — | |
| CAFA2025.09 | — | 8.66 | |
| CoE2025.09 | — | 60.26 | |
| CoT2025.09 | — | 8 | |
| OptiMUSthreshold=0.22025.09 | — | 62.87 | |
| OptiMUSthreshold=0.32025.09 | — | 71.86 | |
| Reflexion2025.09 | — | 9.28 | |
| SAC-Opt-LLMverification=LLM-based2025.09 | — | 73.97 | |
| SAC-Opt-Simverification=similarity-based2025.09 | — | 208.67 | |
| Standard2025.09 | — | 6 |