Predicate Grounding on Kitchen-Worlds
100F1 ScoreSYMBOLIZER
Evaluation Results
| Method | Links | |
|---|---|---|
| SYMBOLIZERBackbone=Gemini 3.1 Pro2026.04 | 100 | |
| SYMBOLIZERBackbone=Mistral Small2026.04 | 100 | |
| SymbolizerModel=Gem.3.1-Pro2026.04 | 85.1 | |
| SYMBOLIZERBackbone=Gemini 3.1 Flash Lite2026.04 | 83.9 | |
| SymbolizerModel=Mistral Small2026.04 | 75.4 | |
| SymbolizerModel=Gem.3.1-FL2026.04 | 69.5 | |
| SYMBOLIZERBackbone=Gem.3.1-Pro2026.04 | 1 | |
| SYMBOLIZERBackbone=Gem.3.1-FL2026.04 | 0.8 | |
| SYMBOLIZERBackbone=Mistral Small2026.04 | 0.7 |