| LEMMA Single-Agent Overall | SG-CoT | Success Rate (SR)80 | | 14 | 1mo ago |
| LEMMA Single-Agent Underspecified | SG-CoT | Success Rate (SR)99 | | 14 | 1mo ago |
| LEMMA Single-Agent Absence | SG-CoT | Success Rate (SR)96 | | 14 | 1mo ago |
| LEMMA Single-Agent Multiplicity | SG-CoT | Success Rate (SR)77 | | 14 | 1mo ago |
| LEMMA Stack and Pass tasks, partially observed (test) | SG-CoT | Success Rate75 | | 8 | 1mo ago |
| OGBench Scene 48 (play) | GCIQL | Success Rate0.51 | | 8 | 1mo ago |
| OGBench AntMaze Giant 48 (stitch) | CDGS | Success Rate84 | | 8 | 1mo ago |
| OGBench PointMaze Giant 48 (stitch) | CDGS | Success Rate82 | | 8 | 1mo ago |
| Robotouille Impossible | | Solved Percentage100 | | 7 | 1mo ago |
| Robotouille Hard | | Solved Rate58.1 | | 7 | 1mo ago |
| Robotouille Easy | | Solved Rate81 | | 7 | 1mo ago |
| Set Table | MoMaStage | Success Rate93.67 | | 6 | 1mo ago |
| Prepare_Groceries | MoMaStage | Success Rate91.67 | | 6 | 1mo ago |
| Tidy_House | MoMaStage | Success Rate85.67 | | 6 | 1mo ago |
| Scene 15 Comprehensive | PlanORN | SR0.32 | | 6 | 1mo ago |
| Comprehensive (Scene 14) | PlanORN | SR89 | | 6 | 1mo ago |
| Comprehensive Scene 13 | OR | SR100 | | 6 | 1mo ago |
| Fan | | Success Rate97.3 | | 3 | 1mo ago |
| Domino | ExoPredicator | Success Rate98.7 | | 3 | 1mo ago |
| Boil | | Success Rate100 | | 3 | 1mo ago |
| Grow | ExoPredicator | Success Rate93.3 | | 3 | 1mo ago |
| Coffee | | Success Rate99.3 | | 3 | 1mo ago |
| Real-world deployment evaluation tasks (held-out evaluation scenarios) | Flow Motion Policy (FMP-100) | Success Rate (Bins)100 | | 2 | 9d ago |