OpenML
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Classification | OpenML 67 datasets CC18 (10-fold cross-validation average) | F1 Score71 | 42 | |
| Multiclass Classification | OpenML 11 multiclass (test) | MacroF1 (Min)44.1 | 42 | |
| Classification | OpenML-cc18 | Average Rank (AUC, Acc, F1)4.99 | 33 | |
| Tabular Classification | OpenML 253 (test) | Accuracy (w/o shift)81.8 | 28 | |
| Regression | Openml_586 | 1-RAE0.1109 | 24 | |
| Semi-supervised Tabular Classification | OpenML 11 (various) | Min Accuracy46.8 | 21 | |
| Regression | OpenML 618 (5-fold cross-validation) | 1-RAE0.0521 | 16 | |
| Regression | OpenML 586 (5-fold cross-validation) | 1-RAE0.1109 | 16 | |
| Tabular Classification | 5 OpenML (train) | Balanced Accuracy76.7 | 13 | |
| Imputation | OpenML MCAR, Missing Probability 0.4 (test) | MAD0 | 13 | |
| Clustering | OpenML 22 datasets | Rank3.61 | 12 | |
| Tabular Classification | OpenML CC18 | Mean Accuracy87.8 | 12 | |
| Conformal Routing Safety Control | OpenML general-purpose (test) | Violation Exceedance Count0 | 12 | |
| Regression | OpenML 361249 | Coverage96.4 | 12 | |
| Regression | OpenML 361247 | Coverage98 | 12 | |
| Regression | OpenML 361243 | Coverage97.9 | 12 | |
| Regression | OpenML 361235 | Coverage97.2 | 12 | |
| Classification | OpenML 72 datasets CC18 (5-fold CV) | Decision Accuracy76.2 | 11 | |
| Dataset Performance-based Similarity Estimation | OpenML datasets | NDCG@10.8811 | 9 | |
| Dataset Retrieval | OpenML ST=0.9 (unseen datasets) | Hit@179.73 | 9 | |
| Dataset Retrieval | OpenML ST=0.8 (unseen datasets) | Hit@185.81 | 9 | |
| Regression | OpenML 620 | 1-RAE0.425 | 9 | |
| Regression | OpenML 618 | 1-RAE0.372 | 9 | |
| Regression | OpenML 616 | 1-RAE0.385 | 9 | |
| Regression | OpenML 607 | 1-RAE0.376 | 9 |
Showing 25 of 77 rows