Semantic Textual Similarity
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.74Spearman's R (Avg)
11
Feb 26, 2026
0.401MSE
10
Jun 30, 2026
75.88Average STS Score
10
Feb 26, 2026
0.595Accuracy
10
Feb 26, 2026
61.08CCC
9
May 27, 2026
85.27Spearman Correlation
9
Apr 15, 2026
76.9Spearman's ρ
9
Feb 26, 2026
87.3Spearman Corr
8
Feb 26, 2026
18.78STSb Score
8
Mar 24, 2026
77.48Spearman Correlation
8
Feb 26, 2026
0.852Pearson Correlation (R)
8
Feb 26, 2026
85.59Pearson R (x100)
8
Feb 26, 2026
0.744Pearson Correlation
8
Feb 26, 2026
65.56JSTS Score
7
Feb 26, 2026
82.74STS Score (Spanish)
7
Feb 26, 2026
86.87Spearman Correlation
6
Jun 23, 2026
0.918Pearson Correlation
6
Feb 27, 2026
77.42STS Score (Clean)
5
Apr 28, 2026
0.62Spearman's Rho
5
Apr 21, 2026
0.83Spearman's Rho
5
Apr 21, 2026
0.83Spearman's rho
5
Apr 21, 2026
0.7Spearman's Rho
5
Apr 21, 2026
74.25Downstream Performance
5
Feb 26, 2026
22.63Latency (ms)
4
May 12, 2026
84.03MRL
4
Apr 28, 2026