| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| LIBERO | Cosmos Policy | Object Achievement100 | 1,025 | 25d ago | |
| LIBERO (test) | CORALSimVLA | Average Success Rate99.3 | 237 | 24d ago | |
| LIBERO | GeoAlign | Spatial Success Rate100 | 223 | 25d ago | |
| LIBERO Object | DEFLECT | Success Rate99.6 | 139 | 1mo ago | |
| SimplerEnv WidowX | Coarse-to-Control | Overall Success Rate83.3 | 123 | 18d ago | |
| SimplerEnv Google Robot tasks Variant Aggregation | ST4VLA | Average Success Rate75.9 | 109 | 1mo ago | |
| RoboTwin Randomized 2.0 | MotuBrain | Overall Success Rate96.1 | 100 | 17d ago | |
| LIBERO | ω-EVA Stage 3 | Spatial Success99 | 90 | 1mo ago | |
| LIBERO simulation | DiT4DiT | Average Success Rate98.6 | 83 | 1mo ago | |
| SimplerEnv Google Robot Visual Matching | Xiaomi-Robotics-0 | Pick Coke Can98.7 | 79 | 1mo ago | |
| SimplerEnv WidowX Robot tasks (test) | LangForce | Success Rate (Spoon)89.6 | 79 | 4mo ago | |
| RoboTwin Clean 2.0 | MotuBrain | Success Rate95.8 | 74 | 17d ago | |
| MimicGen 3-Part Assembly D2 | DiffPo. + O, P | Success Rate64 | 72 | 1mo ago | |
| SimplerEnv Google Robot tasks Visual Matching | Green-VLA | Pick Coke Can Success Rate98.1 | 70 | 1mo ago | |
| CALVIN (ABC->D) | Xiaomi-Robotics-0 | Average Successful Length4.75 | 62 | 3mo ago | |
| LIBERO-Plus Zero-shot | π0.5 + GridS32 | Camera Score82.8 | 59 | 22d ago | |
| LIBERO | VLA-Corrector | Spatial Success Rate100 | 58 | 18d ago | |
| SimplerEnv WidowX Visual Matching | InternVLA-A1.5 | Average Success Rate80.8 | 52 | 18d ago | |
| MimicGen Square D2 | E3Flow | Success Rate70 | 51 | 1mo ago | |
| Adroit | ORCA | Pen Task Score86.7 | 50 | 3mo ago | |
| MimicGen Stack Three D1 | E3Flow | Success Rate100 | 46 | 1mo ago | |
| Libero | π0.5 | Spatial Success Rate98.8 | 46 | 2mo ago | |
| LIBERO LONG | AnchorRefine (X-VLA) | Success Rate97.4 | 44 | 18d ago | |
| LIBERO Average | GEAR-VLA | Success Rate98.7 | 41 | 1mo ago | |
| SimplerEnv WidowX (test) | pi_0.5 | Task Success Rate (Spoon on Towel)79.2 | 41 | 1mo ago |