| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Classification Probing | Cities (test) | Probe Accuracy (Best Layer)100 | 21 | |
| Correctness Prediction | Cities | AUROC88 | 18 | |
| City Identification | Cities NLU Suite | Rank@119.9 | 4 | |
| Decision Making | Cities UK-based participants | Accuracy1.7 | 1 |