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 50 · SOTA2 Research

Question Answering

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

4.72Prefill Speedup Ratio

12

Feb 26, 2026

3.39Prefilling Speedup Ratio

12

Feb 26, 2026

4.14Prefill Speedup Ratio

12

Feb 26, 2026

2WikiMultihopQA

3.57Prefilling Speedup Ratio

12

Feb 26, 2026

ConFiQA (out-of-domain)

GenDiE (Hierarchical inference)

84.63Hit

12

Feb 26, 2026

ASQA (in-domain)

In-context Prompting (gpt-4o)

47.21EM

12

Feb 26, 2026

59.5Accuracy

12

Feb 26, 2026

General Domain QA (ASQA, HotpotQA, NQ, TriviaQA, POPQA)

78ASQA Score

12

Feb 26, 2026

ChineseFactEval

HaluSearch (MCTS)

70.4Accuracy

12

Feb 26, 2026

HaluSearch (MCTS)

43.69Accuracy

12

Feb 26, 2026

80.85PIQA

12

Feb 26, 2026

32Accuracy

12

Feb 26, 2026

SQuAD Dir alpha=0.1 v2

19.91F1 Score

12

Feb 26, 2026

SQuAD Dir alpha=0.1 v2 Standard

21.25F1 Score

12

Feb 26, 2026

36.4F1 Score

12

Feb 26, 2026

36.3Exact Match (EM)

12

Feb 26, 2026

QA Tasks (OpenBookQA, PIQA, ARC-E, ARC-C, SciQ, WebQs) (test)

0.394OpenBookQA

12

Feb 26, 2026

Question Answering

0.19ROUGE-1

12

Feb 26, 2026

World Knowledge Benchmarks Aggregate

63.6Score

12

Feb 26, 2026

Our Trained Model

61.1Accuracy

12

Feb 26, 2026

CausalQA Technology domain (test)

Prompt-based LP-FT

79F1 Score

12

Feb 26, 2026

CausalQA Consumer domain (test)

Prompt-based LP-FT

80.55F1

12

Feb 26, 2026

CausalQA Industrial Setup 1 (test)

Prompt-based LP-FT

80.7F1

12

Feb 26, 2026

text-davinci-002

82.4Accuracy

12

Feb 26, 2026

text-davinci-002

86.9Accuracy

12

Feb 26, 2026

Page 50 of 122

Popular datasets

HotpotQA TriviaQA ARC NQ SQuAD

Follow for updates

Join SOTA2 Contact