| Benchmark | Model | Rank | Results |
|---|---|---|---|
| common-sense-reasoning-on-commonsenseqa | DeBERTaV3-large+KEAR | #2 | Accuracy: 91.2 |
| common-sense-reasoning-on-commonsenseqa | KEAR | #4 | Accuracy: 89.4 |
| common-sense-reasoning-on-commonsenseqa | GPT-3 Direct Finetuned | #15 | Accuracy: 73.0 |