| Benchmark | Model | Rank | Results |
|---|---|---|---|
| question-answering-on-piqa | RoBERTa-large 355M (fine-tuned) | #91 | Accuracy: 77.1 |
| question-answering-on-piqa | GPT-2-small 124M (fine-tuned) | #158 | Accuracy: 69.2 |
| question-answering-on-piqa | BERT-large 340M (fine-tuned) | #163 | Accuracy: 66.8 |
| question-answering-on-piqa | Random chance baseline | #180 | Accuracy: 50 |