| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Object Pickup | BabyAI-Text PickupLocal (No Change) | Success Rate45 | 5 | |
| Object Pickup | BabyAI-Text PickupDist (New Object) | Success Rate71 | 5 | |
| Object Pickup | BabyAI-Text PickupDist (No Change) | Success Rate75 | 5 | |
| Obstacle Navigation | BabyAI-Text GoToLocal (New Object) | Success Rate85 | 5 | |
| Obstacle Navigation | BabyAI-Text GoToLocal (No Change) | Success Rate91 | 5 | |
| Multi-room Exploration | BabyAI-Text FindObj (No Change) | Success Rate23 | 4 | |
| Object Pickup | BabyAI-Text PickupLocal New Object | Success Rate52 | 3 | |
| Multi-room Exploration | BabyAI-Text FindObj New Object | Success Rate20 | 2 | |
| Multi-step Reasoning | BabyAI-Text UnlockLocal (New Object) | Success Rate95 | 2 | |
| Multi-step Reasoning | BabyAI-Text UnlockLocal (No Change) | Success Rate95 | 2 |