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

Factual Question Answering research benchmarks · SOTA2 Research

Factual Question Answering

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

76.52Accuracy

46

Jun 2, 2026

TriviaQA (test)

73Accuracy

29

Feb 26, 2026

79.56Precision

24

Feb 26, 2026

ID Datasets Average

70.82Precision

24

Feb 26, 2026

57.34Precision

24

Feb 26, 2026

76.44Precision

24

Feb 26, 2026

82.1Precision

24

Feb 26, 2026

66.4Truth %

21

May 12, 2026

Factual Category Average (test)

RLVR+QuestionProb

31.38Accuracy

18

Mar 9, 2026

HyGRAG +Inference

72.38Accuracy

16

Jun 17, 2026

SimpleQA (test)

79.07Accuracy

10

Feb 26, 2026

AURATown environment-grounded queries N=50, 3 seeds 1.0

76.6Factual Accuracy

9

Jun 5, 2026

59.9AUROC

4

Mar 26, 2026

TruthfulQA and HotpotQA

19.7Hallucination Rate

3

Apr 7, 2026

Popular datasets

TruthfulQA TriviaQA SciQ PopQA TVQA

Follow for updates

Join SOTA2 Contact