Predicate Grounding on Search and Rescue domain
100F1 ScoreGinSign
Evaluation Results
| Method | Links | |
|---|---|---|
| GinSign2025.12 | 100 | |
| GPT-4o2025.12 | 95.1 | |
| GPT-3.5 Turbo2025.12 | 95 | |
| GPT-4o2025.12 | 94.9 | |
| GPT-3.5 Turbo2025.12 | 94 | |
| GinSign2025.12 | 91.1 | |
| GPT-4.1 Mini2025.12 | 90.9 | |
| GPT-4.1 Mini2025.12 | 87.7 | |
| Lang2LTLdistinguishes_predicate_and_argument=false2025.12 | 77.6 |