| common-sense-reasoning-on-winogrande | ALBERT-base 11M | – | Accuracy: 52.8 |
| common-sense-reasoning-on-winogrande | ALBERT-xxlarge 235M | – | Accuracy: 58.7 |
| common-sense-reasoning-on-winogrande | BERT-base 110M | – | Accuracy: 53.1 |
| common-sense-reasoning-on-winogrande | BERT-large 345M | – | Accuracy: 55.6 |
| common-sense-reasoning-on-winogrande | Random baseline | – | Accuracy: 50 |
| common-sense-reasoning-on-winogrande | RoBERTa-base 125M | – | Accuracy: 56.3 |
| common-sense-reasoning-on-winogrande | RoBERTa-large 355M | – | Accuracy: 54.9 |
| coreference-resolution-on-winograd-schema | ALBERT-base 11M | – | Accuracy: 55.4 |
| coreference-resolution-on-winograd-schema | ALBERT-xxlarge 235M | – | Accuracy: 78.8 |
| coreference-resolution-on-winograd-schema | BERT-base 110M | – | Accuracy: 56.5 |
| coreference-resolution-on-winograd-schema | BERT-large 340M | – | Accuracy: 61.4 |
| coreference-resolution-on-winograd-schema | Random chance baseline | – | Accuracy: 50 |
| coreference-resolution-on-winograd-schema | RoBERTa-base 125M | – | Accuracy: 63 |
| coreference-resolution-on-winograd-schema | RoBERTa-large 354M | – | Accuracy: 73.9 |