| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Binary Classification | TabArena | Elo Rating1,782 | 74 | |
| Multiclass Classification | TabArena Lite | Elo Rating1,662 | 63 | |
| Regression | TabArena Lite | Average Rank1.9 | 56 | |
| Tabular Classification | TabArena Binary | Avg Balanced Accuracy89.32 | 56 | |
| Regression | TabArena Regression | Avg Balanced Acc70.11 | 56 | |
| Multiclass Classification | TabArena Multiclass (6) | Average Balanced Accuracy0.8109 | 56 | |
| Tabular Learning | TabArena | Elo1,663 | 54 | |
| Tabular Prediction | TabArena all 51 datasets | Elo Rating1,800 | 38 | |
| Regression | Tabarena REG | Average Rank3.46 | 32 | |
| Tabular Prediction | TabArena small (full 681 tasks) | Elo Rating1,723 | 26 | |
| Tabular Prediction | TabArena medium 10k-100k (full) | Elo Rating2,146 | 26 | |
| Regression | TabArena | Elo Rating1,959 | 26 | |
| Tabular Classification and Regression | TabArena Lite | Mean Accuracy88.7 | 19 | |
| Tabular Classification | TabArena | Churn Score0.9338 | 12 | |
| Tabular Data Learning | TabArena-Lite | Elo Rating1,651 | 11 | |
| Binary Classification | TabArena Customer v0.1 (test) | ROC AUC0.738 | 10 | |
| Tabular Foundation Model Pretraining | TabArena 38 classification tasks subsampled 2025 (5-fold CV) | Time (min)0.92 | 9 | |
| Classification | Tabarena CLS | AUC0.8638 | 9 | |
| Multiclass Classification | TabArena Multiclass v1 (test) | Rank2.3 | 6 | |
| Binary Classification | TabArena Binary v1 (test) | Rank2.1 | 6 | |
| Classification | TabArena All v1 (test) | Rank2.3 | 6 | |
| Tabular Classification | TabArena (3 outer-fold averages) | Churn Accuracy92.66 | 4 |