Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

NarrativeQA dataset and benchmarks – Page 3 · SOTA2 Research

Research Datasets

NarrativeQA

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Question Answering

NarrativeQA Peter Rabbit

16Exact Match

4

Question Answering

NarrativeQA

3.212R@1

4

Question Answering

NarrativeQA (dev)

31.6ROUGE-L

4

Multi-mention reading comprehension

NarrativeQA (test)

58.8ROUGE-L

4

Reading Comprehension

NarrativeQA Story Summaries (test)

42BLEU-1

4

Long-context Question Answering

NarrativeQA LongBench (test)

11.48String Match

3

Question Answering

NarrativeQA SCROLLS (test)

11.63F1 Score

3

Long-document understanding

NarrativeQA

88.5Score (avg@3)

3

Question Answering

NarrativeQA Robinson Crusoe

40Exact Match

3

Question Answering

NarrativeQA The Phantom of the Opera 25k nodes, 56k edges

34Exact Match (EM)

3

Question Answering

NarrativeQA

97.71Latency (s)

3

Multi-mention reading comprehension

NarrativeQA (dev)

58.1ROUGE-L

3

Question Answering

NarrativeQA (dev)

25.4EM

2

Page 3 of 3

Popular tasks

Question Answering Long-context Question Answering Reading Comprehension Multi-mention reading comprehension Latency Evaluation

Follow for updates

Join SOTA2 Contact