Binary Classification on BoolQ HELM
89.75Balanced AccuracyS-StackingNet
Evaluation results
| Method | Links | |
|---|---|---|
| S-StackingNetMode=Supervised2026.02 | 89.75 | |
| U-StackingNetMode=Unsupervised2026.02 | 89.24 | |
| Base-Best2026.02 | 89.21 | |
| Logistic RegressionMode=Supervised2026.02 | 89.13 | |
| PM2026.02 | 88.76 | |
| M-MSR2026.02 | 88.41 | |
| WAwA2026.02 | 88.26 | |
| EBCC2026.02 | 88.26 | |
| LA2026.02 | 88.25 | |
| KOS2026.02 | 88.24 | |
| SML2026.02 | 88.24 | |
| GLAD2026.02 | 88.23 | |
| ZenCrowd2026.02 | 88.16 | |
| Dawid-Skene2026.02 | 88.01 | |
| MACE2026.02 | 87.74 | |
| LAA2026.02 | 87.73 | |
| Voting2026.02 | 87.29 | |
| Base-Worst2026.02 | 64.13 |