List your company

ResearchFormerly WizWand

NarrativeQA

Benchmarks

TaskDatasetSOTA resultTrendResults

Prompt Injection Attack

NarrativeQA

86ASR

11

Long-context Question Answering

NarrativeQA

61.7Exact Match

11

Reading Comprehension

NarrativeQA

6.804Overall Score

10

Question Answering

NarrativeQA

40.28F1 Score

10

Context Traceback

NarrativeQA LongBench

96Precision

10

English Reading

NarrativeQA

53.35F1 Score

9

Question Answering

NarrativeQA

58.08Ragas Answer Relevance

9

Question Answering

NarrativeQA Helmet benchmark

49.5F1 Score

9

Question Answering

NarrativeQA Trun. latest (test)

21.34Average Score

9

NarrativeQA

29.11Recall@3

8

Reading Comprehension

NarrativeQA (test)

54.11BLEU-1

8

Reading Comprehension

NarrativeQA summaries

36.55BLEU-1

8

Open-ended Question Answering

NarrativeQA

73.77Accuracy

7

Long-context Question Answering

NarrativeQA

59.5R@10

6

Payload-splitting attack detection

NarrativeQA

84Precision

6

Question Answering

NarrativeQA

24,686.84Prefill Throughput (tok/s)

6

Latency Evaluation

NarrativeQA

2.1End-to-End Latency

6

Question Answering

NarrativeQA summaries (test)

43.63BLEU-1

6

Reading Comprehension

NarrativeQA Story Summaries (val)

52.78BLEU-1

6

Narrative planning

NarrativeQA novel-to-video adaptation setting

4.26CBC

5

Question Answering

NarrativeQA

62.2Exact Match (EM)

5

Question Answering

NarrativeQA

25.39BLEU

5

Question Answering

NarrativeQA

32.6F1 Score

5

Knowledge Base Construction

NarrativeQA

40.58KB Construction Time

5

Question Answering

NarrativeQA

12.47F1 Score

5