Optimization Modeling on ReSocratic
88.7AccuracySAC-Opt
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SAC-Opt2025.09 | 88.7 | 79.85 | |
| SAC-OptBackbone=GPT-4o, Number of runs=52025.09 | 88.7 | — | |
| SAC-Opt2025.09 | 88.7 | — | |
| Best-baseline2025.09 | 81 | 74.23 | |
| OptiMUS-0.3Backbone=GPT-4o, Number of runs=52025.09 | 81 | — | |
| OptiMUSversion=0.32025.09 | 81 | — | |
| ReflexionBackbone=GPT-4o, Number of runs=52025.09 | 76.1 | — | |
| Reflexion2025.09 | 76.1 | — | |
| OptiMUS-0.2Backbone=GPT-4o, Number of runs=52025.09 | 75.8 | — | |
| OptiMUSversion=0.22025.09 | 75.8 | — | |
| CoEreferenced=true2025.09 | 71.2 | — | |
| Standardreferenced=true2025.09 | 48.4 | — | |
| CoTreferenced=true2025.09 | 43.6 | — | |
| CAFAreferenced=true2025.09 | 40.1 | — | |
| CAFA2025.09 | — | 8.11 | |
| CoE2025.09 | — | 80.45 | |
| CoT2025.09 | — | 8.65 | |
| OptiMUSthreshold=0.22025.09 | — | 51.05 | |
| OptiMUSthreshold=0.32025.09 | — | 74.23 | |
| Reflexion2025.09 | — | 9.28 | |
| SAC-Opt-LLMverification=LLM-based2025.09 | — | 79.85 | |
| SAC-Opt-Simverification=similarity-based2025.09 | — | 174.99 | |
| Standard2025.09 | — | 6.3 |