| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Spatial and Temporal Simulation Tasks Episode-level | Cortex (full harness) | Subtask Accuracy3.576 | 7 | 18d ago | |
| Spatial and Temporal Simulation Tasks Step-level | Cortex (full harness) | Subtask Accuracy3.909 | 7 | 18d ago | |
| Real-world (test) | AnnotateAnything | Success Rate12 | 1 | 1mo ago |