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

Semantic Textual Similarity research benchmarks – Page 2 · SOTA2 Research

Semantic Textual Similarity

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

STS Benchmark (dev)

0.926Pearson Correlation (r)

21

Feb 26, 2026

STS tasks (test)

Pretended CoT w/ ReverseEOL

72.38STS12 Score

20

Jun 5, 2026

0.76Pearson Correlation

17

Feb 26, 2026

2.68Leakage

16

Feb 26, 2026

BERTlarge-flow (target)

77.63Spearman Rho (x100)

16

May 29, 2026

76.52Spearman's Rho

16

May 29, 2026

72.56Spearman Rho (x100)

16

May 29, 2026

0.766Spearman's Rho

15

May 29, 2026

E5-MISTRAL with LiRA

76.55Pearson Correlation

14

May 19, 2026

SemEval-2022 Task 2 Idiomatic STS (evaluation)

Adaptive Contrastive Triplet Loss

0.69Spearman Rho (All)

14

Feb 26, 2026

STSb TR (train)

emrecan/bert-base-tr-nli-stsb-tr

93.79Pearson Correlation

13

May 29, 2026

emrecan/bert-base-tr-nli-stsb-tr

83.45Pearson Correlation

13

May 29, 2026

77.43Spearman Correlation

13

Apr 28, 2026

84.47Spearman Correlation (100x)

13

Apr 28, 2026

71.23Score

13

Mar 25, 2026

95.94PICP

12

May 18, 2026

Multilingual STS low-resource languages

Synth - Prompting

81.4STS Score (Afr)

12

Mar 4, 2026

0.767Spearman Correlation

12

Feb 26, 2026

STS Benchmarks (STSB, FinPara, SICK-R, SemRel24, STS12, STS13, STS14, STS15, STS17, STS22) (test)

87.55STSB Score

11

Feb 26, 2026

0.341Pearson Correlation

11

Feb 26, 2026

0.428Pearson Correlation

11

Feb 26, 2026

0.313Pearson Correlation

11

Feb 26, 2026

0.692Pearson Correlation

11

Feb 26, 2026

0.6Pearson Correlation

11

Feb 26, 2026

0.482Pearson Correlation

11

Feb 26, 2026

Page 2 of 4

Popular datasets

STS STS-B SICK STSb KorSTS

Follow for updates

Join SOTA2 Contact