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

Sarcasm Detection research benchmarks – Page 2 · SOTA2 Research

Sarcasm Detection

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

74Accuracy

6

Feb 26, 2026

SARC Main 1.0 (imbalanced)

79Accuracy

6

Feb 26, 2026

SARC Main 1.0 (balanced)

77Accuracy

6

Feb 26, 2026

SpeechPrompt v2 (pGSLM+)

78.7F1 Score

5

Feb 26, 2026

75F1 Score

5

Feb 26, 2026

69F1 Score

5

Feb 26, 2026

Generated data sitcom-derived (test)

71.4Precision

4

Jun 16, 2026

Proposed detector

71.3Precision

4

Jun 16, 2026

Sarcasm dataset

58.14Macro F1

4

Mar 5, 2026

53.57F1 Macro

3

Feb 26, 2026

MUStARD (5-fold CV)

74.42Accuracy

2

Jun 5, 2026

PodSarc 1,000-utterance stratified random subset (5-fold CV)

63.6Accuracy

1

Jun 5, 2026

MUStARD++ (5-fold CV)

73.29Accuracy

1

Jun 5, 2026

Page 2 of 2

Popular datasets

MUSTARD SARC Sarcasm SC Twitter

Follow for updates

Join SOTA2 Contact