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

Fact Verification research benchmarks – Page 2 · SOTA2 Research

Fact Verification

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

FEVER-Symmetric

88Precision

16

Feb 26, 2026

X-Fact Zero-Shot (ZS)

30Macro-F1

15

May 27, 2026

X-Fact Out-of-Domain (OOD)

41Macro-F1

15

May 27, 2026

X-Fact In-Domain (ID)

67Macro-F1

15

May 27, 2026

99.44Accuracy

15

Feb 26, 2026

71Macro F1

14

Apr 21, 2026

FEVER 1.0 (test)

74.07Label Accuracy

14

Feb 26, 2026

61.17F1 Score

12

Jul 7, 2026

84Macro F1

12

Jun 30, 2026

GraphRAG + GeoRAG

77.2Accuracy

12

Jun 30, 2026

0Oracle Gap (pp)

12

Jun 25, 2026

0Oracle Gap (pp)

12

Jun 25, 2026

54Accuracy (%)

12

Feb 26, 2026

54Accuracy

12

Feb 26, 2026

61.4Accuracy

12

Feb 26, 2026

73.73Accuracy

11

Feb 26, 2026

InfoTabs (test)

MiniCPM-V-2.6 8B

75.74Accuracy

11

Feb 26, 2026

93.2Accuracy

10

Jun 4, 2026

POLITIFACT HIDDEN (test)

83.6Accuracy

10

Apr 23, 2026

77.6Accuracy

10

Mar 18, 2026

99.7Accuracy

10

Mar 18, 2026

PubHealthTab OOD (test)

Qwen3-VL-8B-DISCO

77.14Accuracy

10

Feb 26, 2026

78Accuracy

9

Feb 26, 2026

FACTKG 1.0 (test)

72.7Accuracy

9

Feb 26, 2026

Symmetric FEVER 1.0 (test)

85.88Accuracy

9

Feb 26, 2026

Page 2 of 4

Popular datasets

FEVER InfoTabs CREAK X-Fact TabFact

Follow for updates

Join SOTA2 Contact