| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| CALVIN | WAM | Success Rate96.6 | 7 | 1mo ago | |
| Real-world | SADP | Success Rate86.7 | 6 | 2mo ago | |
| Real-world Tabletop Manipulation Close Drawer | RL-Co | Success Rate100 | 6 | 5mo ago | |
| Simpler-Env | EVE | Success Rate76.3 | 6 | 5mo ago | |
| RLBench | ICon-Diff-T | Success Rate91.3 | 5 | 5mo ago | |
| UR5 robot dataset (test) | π0 | Success Rate90 | 4 | 2mo ago | |
| Franka Real-world Environment | Success Rate90 | 4 | 3mo ago | ||
| Real-world Evaluation 1.0 (unseen object placements) | VERM | Success Rate100 | 4 | 5mo ago | |
| CALVIN Generalization 10% (transfer) | TF-CLAM | Success Rate33 | 3 | 1mo ago | |
| Real World (test) | CAP-AGENT0 + RATS Skills (MolmoSpaces) | Successes Count8 | 2 | 1mo ago | |
| Real Robot | Object-Centric Residual RL | Success Rate20 | 2 | 1mo ago | |
| Simulation | Object-Centric Residual RL | Success Rate19.7 | 2 | 1mo ago | |
| Real-World custom 7-DOF robot arm | RetoVLA | Success Rate96 | 2 | 4mo ago | |
| Real-robot PiPER 1.0 (test) | AnchorDream | Success Rate75 | 2 | 5mo ago | |
| Real-world 1.0 (test) | OpenVLA-OFT | Success Rate50 | 2 | 5mo ago | |
| Robot Manipulation In-scene Videos (test) | - | - | 0 | 5mo ago |