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

GovReport dataset and benchmarks · SOTA2 Research

Research Datasets

GovReport

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Language Modeling

GovReport

2.5Perplexity

50

Document Summarization

GovReport (test)

75.56ROUGE-1

50

Long-context language generation

GovReport

3.36Speedup (×)

32

Long-context Input (Summarization)

GovReport

3.09Speedup

31

GovReport

46ROUGE Score

30

GovReport (val)

47.2ROUGE-L

17

Document Summarization

GovReport

60.64ROUGE-1

15

Document Summarization

GovReport

89ASR Score

14

GovReport

17.4Token MAE

14

Context Compression

GovReport

61.39ROUGE-1

13

GovReport (test)

0.555ROUGE-1

13

GovReport 16K

11895th Percentile Latency (ms)

12

Long-Context Summarization

GovReport

22.03ROUGE-1 Score

12

Prompt Injection Attack

GovReport

0Attack Success Rate (ASR)

11

Long-Context Summarization

GovReport (test)

16.11ROUGE-1

10

Plain Summarization

GovReport

46.93ROUGE-1

9

Document Summarization

GovReport

18.43G-mean

9

Long-context Question Answering

GovReport

68.4C Score

9

Long-context answering with citations

GovReport

82.8Citation Recall

9

GovReport

0.92BERTScore

7

Extractive Summarization

GovReport (GR)

75.3Accuracy

5

Text Simplification

GovReport 500 samples (human evaluation)

4.27Coherence

4

Prompt Injection Attack

GovReport

100ASR

4

Summarization Evaluation (Human Correlation)

GovReport (test)

61Relevance

4

GovReport SCROLLS (test)

48.18ROUGE-1

3

Page 1 of 2

PreviousNext

Popular tasks

Summarization Document Summarization Long-context Summarization Prompt Injection Attack Long-context Question Answering

Follow for updates

Join SOTA2 Contact