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

Text Classification research benchmarks – Page 17 · SOTA2 Research

Text Classification

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

SetFit FTC-metadataset mini 10% 1.0 (test)

95.54AURAC

8

Feb 26, 2026

SST-2 FTC-metadataset mini 10% 1.0 (test)

98.28AURAC

8

Feb 26, 2026

FTC-metadataset News mini 10% 1.0 (test)

G50 r.c.o. JUCAL

0.978AURAC

8

Feb 26, 2026

DBpedia FTC-metadataset mini 10% 1.0 (test)

0.99AUC

8

Feb 26, 2026

Yahoo @256 (test)

67.2Accuracy

8

Feb 26, 2026

Retweets (full)

66.5Accuracy

8

Feb 26, 2026

LLM Detect (full)

90.7Accuracy

8

Feb 26, 2026

Citations (full)

64.6Accuracy

8

Feb 26, 2026

Headlines (full)

67Accuracy

8

Feb 26, 2026

Dreaddit (full)

82.3Accuracy

8

Feb 26, 2026

71.5Accuracy

8

Feb 26, 2026

89Accuracy

8

Feb 26, 2026

SEMEVAL real-world noise

81.47Accuracy

8

Feb 26, 2026

TREC real-world noise

78.84Accuracy

8

Feb 26, 2026

ChemProt real-world noise

70.98Accuracy

8

Feb 26, 2026

90Accuracy

8

Feb 26, 2026

92Accuracy

8

Feb 26, 2026

0.89Accuracy

8

Feb 26, 2026

TweetEval Offensive (test)

69.14Accuracy

8

Feb 26, 2026

TweetEval Hate (test)

55.72Accuracy

8

Feb 26, 2026

LRA Text 4,096 1.0 (test)

88.88Accuracy

8

Feb 26, 2026

Random -> Random

48.83Accuracy

8

Feb 26, 2026

Unspecified Dataset Class -> Non-Class

42.8Accuracy

8

Feb 26, 2026

Amazon-Review single-domain generalization (test)

76.42Class D Score

8

Feb 26, 2026

Yelp 560k (test)

DistilBERT Supervised

95.42Accuracy

8

Feb 26, 2026

Page 17 of 29

Popular datasets

AG News SST IMDB AGNews SST-2

Follow for updates

Join SOTA2 Contact