| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| EB-Manipulation | Claude-3.7 | Average Score42 | 16 | 1mo ago | |
| RLBench Few-shot Adaptation Tasks (test) | SAM-E | Meat on Grill Success Rate84 | 12 | 4mo ago | |
| Guava Simulation (Overall) | Guava-Agent-4B | Success Rate75.6 | 4 | 1mo ago | |
| Guava Simulation OOD Long Horizon | Guava-Agent-4B | Success Rate: Separate Food and Utensils93.3 | 4 | 1mo ago | |
| Guava Simulation (OOD Prompt) | Stack Cube (Reverse Order) Success Rate100 | 4 | 1mo ago | ||
| Guava Simulation (OOD Object) | CaP-Agent0 | Success Rate (Pick Up Carrot)100 | 4 | 1mo ago | |
| Guava Simulation (ID) | Success Rate: Place Can in Box100 | 4 | 1mo ago | ||
| Simpler WidowX | ER-1 + Ours (E-TTS) | Spoon on Towel Success Rate65.27 | 3 | 29d ago | |
| VLaBench Track 6 | π0.5 | Action Completion (AC)0.46 | 2 | 29d ago | |
| VLaBench Track 4 | E-TTS | AC16 | 2 | 29d ago | |
| VLaBench Track 3 | E-TTS | AC18 | 2 | 29d ago | |
| VLaBench Track 2 | E-TTS | AC8 | 2 | 29d ago | |
| VLaBench Track 1 | E-TTS | Action Completion (AC)54 | 2 | 29d ago | |
| RLBench 10 tasks suite (test) | Hiveformer | Pick and Lift Success Rate88.9 | 1 | 4mo ago |