Model Ranking Prediction on Reasoning Tasks Aggregate
0.81Spearman RhoRankSVM (RBF)
Evaluation Results
| Method | Links | |
|---|---|---|
| RankSVM (RBF)Protocol=Leave-2-tasks-out cross-validated, Subsampling Seeds=202026.05 | 0.81 | |
| RankSVM (linear)Protocol=Leave-2-tasks-out cross-validated, Subsampling Seeds=202026.05 | 0.81 | |
| 3-sparse proxyProtocol=Leave-2-tasks-out cross-validated, Subsampling Seeds=202026.05 | 0.78 | |
| Univariate proxyProtocol=Leave-2-tasks-out cross-validated, Subsampling Seeds=202026.05 | 0.54 | |
| FineWeb CE lossProtocol=Leave-2-tasks-out cross-validated2026.05 | 0.36 | |
| rBridgeProtocol=Leave-2-tasks-out cross-validated2026.05 | 0.33 |