Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Audio Generation on MMAU Speech (Clean)
Loading...
99
GSR
SEEN
89.64
92.07
94.5
96.93
Jan 12, 2026
GSR
Updated 1mo ago
Evaluation Results
Method
Method
Links
GSR
SEEN
Model=Qwen
2026.01
99
SEEN
Model=MiniCPM
2026.01
98
STFT
Model=Qwen
2026.01
97
WT
Model=Qwen
2026.01
97
SEEN
Model=StepAudio
2026.01
96.33
WT
Model=StepAudio
2026.01
94.67
STFT
Model=MiniCPM
2026.01
94
STFT
Model=StepAudio
2026.01
93.33
WT
Model=MiniCPM
2026.01
93
Segan
Model=MiniCPM
2026.01
93
DFL
Model=MiniCPM
2026.01
93
DFL
Model=StepAudio
2026.01
92.33
DFL
Model=Qwen
2026.01
92
Segan
Model=Qwen
2026.01
91.33
Segan
Model=StepAudio
2026.01
90
Feedback
Search any
task
Search any
task
