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

Hate Speech Detection research benchmarks · SOTA2 Research

Hate Speech Detection

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

NHP Context-Free Data Aug.

90.51Accuracy

49

Feb 26, 2026

HateXplain (test)

X-MuTeST with LLM

85.13Macro F1 Score

44

Jun 29, 2026

84.8Total F1

35

Jun 18, 2026

74.22Accuracy

30

Mar 5, 2026

57F1-macro

27

May 19, 2026

89.7Accuracy

25

Feb 26, 2026

89.2Accuracy

25

Feb 26, 2026

78.4F1 Score

24

Jun 18, 2026

62F1 Score

24

Jun 18, 2026

gated demographic residual model

76.8Accuracy

19

May 27, 2026

LLaMA-3.2-1B-LoRA

81.83Accuracy

19

May 27, 2026

93.13Accuracy

15

Apr 13, 2026

HateXplain (held-out)

47.3F1 Score

14

Feb 26, 2026

0.937Accuracy

14

Feb 26, 2026

HateWas v1 (test)

57.65Macro F1

14

Feb 26, 2026

Stormfront → GHC (test)

57.2Source F1

14

Feb 26, 2026

HatEval → GHC (test)

0.642Source F1

14

Feb 26, 2026

Stormfront -> GHC 94 mins annotation (test)

59.5Source F1

14

Feb 26, 2026

HatEval -> GHC 80 mins annotation (test)

63.7Source F1

14

Feb 26, 2026

12Avg Exit

12

Mar 10, 2026

12Avg Exit

12

Mar 10, 2026

12AvgExit

12

Mar 10, 2026

Hate Speech Detection (test)

BERT-base + RL-MTL

72.06Macro F1

12

Feb 26, 2026

55Total F1 Score

11

Mar 12, 2026

73.6Accuracy

11

Feb 26, 2026

Page 1 of 3

PreviousNext

Popular datasets

HatEval HateXplain ETHOS LT-EDI LGBTQ+ Hate Speech Detection Meme Dataset GHC

Follow for updates

Join SOTA2 Contact