Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Speech-to-Speech Question Answering on AlpacaEval
Loading...
72.22
Accuracy
VocalNet
11.588
27.329
43.07
58.811
Mar 10, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
VocalNet
Model Parameters=8B
2026.03
72.22
Qwen2.5-Omni-7B
Model Parameters=7B
2026.03
67.17
SPEECH-OMNI-LITE
Model Parameters=8B
2026.03
65.66
LLaMA-Omni2
Model Parameters=7B
2026.03
63.64
GLM-4-Voice
Model Parameters=9B
2026.03
58.59
Freeze-Omni
Model Parameters=7B
2026.03
28.79
Baichuan-Omni-1.5
Model Parameters=7B
2026.03
13.92
Feedback
Search any
task
Search any
task