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

SOMOS dataset and benchmarks · SOTA2 Research

Research Datasets

SOMOS

Benchmarks

Task NameDataset NameSOTA MethodSort

Task NameDataset NameSOTA ResultTrendResults

Mean Opinion Score Prediction

SOMOS large-scale (test)

0.404LCC

16

Preference Evaluation

SOMOS

60Acc@0.5

15

Speech Quality Assessment

SOMOS

0.68LCC

12

Speech Quality Evaluation

SOMOS (Full)

0.235PCC

5

Speech Quality Evaluation

SOMOS Clean

0.261PCC

5

Pairwise preference prediction

SOMOS NM MOS-derived (test)

74.72Accuracy

4

Pairwise preference prediction

SOMOS M MOS-derived (test)

73.27Accuracy

4

System-level MOS Prediction

SOMOS Std

0.161MSE

2

Subjective reliability estimation

SOMOS

—Primary metric

0

Popular tasks

Speech Quality Evaluation Pairwise Preference Prediction Preference Evaluation Speech Quality Assessment Subjective reliability estimation

Follow for updates

Join SOTA2 Contact