Planning on ProDG Cooking
100Planning Success RateSymbolizer
Evaluation Results
| Method | Links | |
|---|---|---|
| SymbolizerModel=Gem.3.1-FL2026.04 | 100 | |
| SymbolizerModel=Gem.3.1-Pro2026.04 | 96.7 | |
| ViLaInModel=Gem. 3.1-FL, Retries=2 retries2026.04 | 90 | |
| ViLaInModel=GPT-4, Retries=2 retries2026.04 | 71 | |
| ViLaInModel=Gem. 3.1-FL, Retries=no retry2026.04 | 70 | |
| SymbolizerModel=Mistral Small2026.04 | 66.7 | |
| ViLaInModel=GPT-4, Retries=no retry2026.04 | 9 |