| Benchmark | Model | Rank | Results |
|---|---|---|---|
| question-answering-on-narrativeqa | Masque (NarrativeQA + MS MARCO) | – | Rouge-L: 59.87BLEU-1: 54.11BLEU-4: 30.43METEOR: 26.13 |
| question-answering-on-narrativeqa | Masque (NarrativeQA only) | – | Rouge-L: 54.74BLEU-1: 48.7BLEU-4: 20.98METEOR: 21.95 |