Natural Language to Optimization on NLP4LP (test)
90.5Success RateNC2C
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| NC2CModel=GPT-5.12026.01 | 90.5 | 94.2 | |
| NC2CModel=Qwen3-235B-A22B2026.01 | 86.5 | 91 | |
| OptiMUSModel=GPT-5.12026.01 | 85.4 | 90.5 | |
| Chain-of-ExpertsModel=GPT-5.12026.01 | 82 | 88.2 | |
| ReflexionModel=GPT-5.12026.01 | 81.2 | 88 | |
| OptiMUSModel=Qwen3-235B-A22B2026.01 | 80.2 | 87 | |
| VanillaModel=GPT-5.12026.01 | 78.5 | 85.3 | |
| Chain-of-ExpertsModel=Qwen3-235B-A22B2026.01 | 76.5 | 83.2 | |
| ReflexionModel=Qwen3-235B-A22B2026.01 | 74.5 | 82.5 | |
| VanillaModel=Qwen3-235B-A22B2026.01 | 72.3 | 80.1 |