Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Spoken Question Answering on AlpacaEval
Loading...
3.88
WER
LLaMA-Omni2
0.574
22.8895
45.205
67.5205
Mar 10, 2026
WER
UTMOS
Updated 1mo ago
Evaluation Results
Method
Method
Links
WER
UTMOS
LLaMA-Omni2
Parameters=7B
2026.03
3.88
4.43
Qwen2.5-Omni-7B
Parameters=7B
2026.03
5.54
4.2
VocalNet
Parameters=8B
2026.03
7.43
4.49
SPEECH-OMNI-LITE
Parameters=8B
2026.03
23.77
3.73
GLM-4-Voice
Parameters=9B
2026.03
29.44
3.86
Freeze-Omni
Parameters=7B
2026.03
49.47
4.14
Baichuan-Omni-1.5
Parameters=7B
2026.03
86.53
4.3
Feedback
Search any
task
Search any
task