Optimization Modeling on ComplexLP
79.6AccuracySAC-Opt
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SAC-Opt2025.09 | 79.6 | 40.96 | |
| SAC-OptBackbone=GPT-4o, Number of runs=52025.09 | 79.6 | — | |
| SAC-Opt2025.09 | 79.6 | — | |
| Standardreferenced=true2025.09 | 57.7 | — | |
| Best-baseline2025.09 | 52.1 | 8.22 | |
| OptiMUS-0.3Backbone=GPT-4o, Number of runs=52025.09 | 52.1 | — | |
| OptiMUSversion=0.32025.09 | 52.1 | — | |
| CoEreferenced=true2025.09 | 50.6 | — | |
| OptiMUS-0.2Backbone=GPT-4o, Number of runs=52025.09 | 45.8 | — | |
| OptiMUSversion=0.22025.09 | 45.8 | — | |
| CAFAreferenced=true2025.09 | 44.5 | — | |
| ReflexionBackbone=GPT-4o, Number of runs=52025.09 | 43.2 | — | |
| Reflexion2025.09 | 43.2 | — | |
| CoTreferenced=true2025.09 | 42.3 | — | |
| CAFA2025.09 | — | 9.48 | |
| CoE2025.09 | — | 70.97 | |
| CoT2025.09 | — | 10.16 | |
| OptiMUSthreshold=0.22025.09 | — | 48.63 | |
| OptiMUSthreshold=0.32025.09 | — | 89.61 | |
| Reflexion2025.09 | — | 14.28 | |
| SAC-Opt-LLMverification=LLM-based2025.09 | — | 40.96 | |
| SAC-Opt-Simverification=similarity-based2025.09 | — | 173.76 | |
| Standard2025.09 | — | 8.22 |