| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| ICU-Sepsis | DualDICE | Bias-0.759 | 8 | 1mo ago | |
| Sepsis simulator | FF-OIS | Bias0.001 | 8 | 1mo ago | |
| Suboptimal-RoboSuite Value-Bench | WVM | Hesitation RMSE0.04 | 7 | 1mo ago | |
| Suboptimal-Value-Bench ARX | WVM | Hesitation RMSE0.05 | 7 | 1mo ago | |
| Suboptimal-Value-Bench AgileX | WVM | Hesitation RMSE0.07 | 7 | 1mo ago | |
| Suboptimal-Value-Bench AgileX (retry segments) | WVM | Retry-VOC0.79 | 5 | 1mo ago | |
| Suboptimal-Value-Bench RoboSuite (retry segments) | WVM | Retry-VOC0.75 | 4 | 1mo ago | |
| Suboptimal-Value-Bench ARX (retry segments) | WVM | Retry VOC0.79 | 4 | 1mo ago | |
| Real-robot manipulation tasks (Pick up Spoon, Stack Blocks, Fold Towel, Open Drawer) (held-out) | Robometer | VOC99.4 | 4 | 1mo ago |