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

Question Answering research benchmarks – Page 118 · SOTA2 Research

Question Answering

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

CausalQA (test)

Prompt-based LP-FT

85.53F1 Score

2

Feb 26, 2026

Prompt-based LP-FT

85.4F1 Score

2

Feb 26, 2026

36.67Accuracy

2

Feb 26, 2026

19.62Accuracy

2

Feb 26, 2026

WorldTreeQA (test)

50.7Accuracy (All)

2

Feb 26, 2026

23.37ROUGE-1

2

Feb 26, 2026

28.44ROUGE-1

2

Feb 26, 2026

28.44ROUGE-1

2

Feb 26, 2026

ELI5 unseen (test)

13.97ROUGE-1

2

Feb 26, 2026

GooAQ-S unseen (test)

21.93ROUGE-1 Score

2

Feb 26, 2026

WikiCQA seen (test)

24.1ROUGE-1

2

Feb 26, 2026

GENIE - ARC-DA w/o IR (test)

Khashabi et al.

72Human Accuracy

2

Feb 26, 2026

37.6Exact Match

2

Feb 26, 2026

NarrativeQA (dev)

25.4EM

2

Feb 26, 2026

40.6F1

2

Feb 26, 2026

Fast Post-Training Pruning Framework

1.34Latency Speedup

2

Feb 26, 2026

0.851MAP

2

Feb 26, 2026

SQuAD fine-tuning 1.1

91.29F1 Score

2

Feb 26, 2026

Ours 1-hop generated QA dataset (test)

88.2EM

2

Feb 26, 2026

Ours 2-hop generated QA dataset (test)

50.6EM

2

Feb 26, 2026

GPT2 generated QA dataset (test)

66.9EM

2

Feb 26, 2026

DP-Graph generated QA dataset (test)

55.2EM

2

Feb 26, 2026

HotpotQA May 2020 (leaderboard)

74.2F1 Score

2

Feb 26, 2026

TriviaQA May 2020 (leaderboard)

Longformer-large

77.3F1

2

Feb 26, 2026

WikiHop May 2020 (leaderboard)

Longformer-large

81.9F1 Score

2

Feb 26, 2026

Page 118 of 122

Popular datasets

HotpotQA TriviaQA ARC NQ SQuAD

Follow for updates

Join SOTA2 Contact