Spoken Dialogue Evaluation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
1.08Repeat Rate
16
Feb 26, 2026
93.07TIF
10
Feb 26, 2026
4.5Alpa Score
8
Jun 4, 2026
9.19Phonetic Error
7
May 11, 2026
48.28Phonetic Score
7
May 11, 2026
39.33Semantic Memory Pass Ratio
6
Jun 16, 2026
84.8MaJ
4
May 26, 2026
86.6MaJ
4
May 26, 2026