| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| SICK (test) | NeuralLog (full system) | Accuracy90.3 | 21 | 4d ago | |
| Levy/Holt (test) | EGT2-L3 | AUPRC0.356 | 11 | 4d ago | |
| Berant (test) | EGT2-L3 | AUPRC44.3 | 9 | 4d ago | |
| SNLI (test) | SDM-ATTACK | Attack Success Rate85.5 | 6 | 4d ago | |
| FewGLUE CB (CommitmentBank) few-shot (32 examples) (dev) | iPET (ALBERT) | F1 Score92.4 | 6 | 4d ago | |
| FewGLUE CB (CommitmentBank) few-shot (32 examples) (test) | iPET (ALBERT) | F1 Score79.9 | 4 | 4d ago |
