| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-step outcome prediction | RW MIMIC-extract (Latino) | RMSE4.57 | 36 | |
| Multi-step outcome prediction | RW MIMIC-extract (Asian) | RMSE4.69 | 36 | |
| Off-policy prediction | RW tabular | Tail-average RMSE0.023 | 16 | |
| Word Similarity | EN RW | Spearman Correlation48 | 10 | |
| Off-policy prediction | RW inverted | Tail-average RMSE0.035 | 8 | |
| Integer Linear Programming Solving | RW | Objective Value77.5 | 7 | |
| Semantic Segmentation | RW-10 | mIoU44.8 | 4 | |
| Autonomous Navigation | RW Baseline Difficult Forest 1.0 | Distance (m)57 | 2 | |
| Word Similarity | RW (test) | Spearman Correlation58.12 | 2 |