| Benchmark | Model | Rank | Results |
|---|---|---|---|
| question-answering-on-boolq | BERT-MultiNLI 340M (fine-tuned) | #43 | Accuracy: 80.4 |
| question-answering-on-boolq | BiDAF-MultiNLI (fine-tuned) | #56 | Accuracy: 75.57 |
| question-answering-on-boolq | GPT-1 117M (fine-tuned) | #63 | Accuracy: 72.87 |
| question-answering-on-boolq | BiDAF + ELMo (fine-tuned) | #66 | Accuracy: 71.41 |
| question-answering-on-boolq | Majority baseline | #87 | Accuracy: 62.17 |