Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety on Advbench
Loading...
100
SafetyJudge Score
Kimi-Audio
74.416
81.058
87.7
94.342
Sep 9, 2025
SafetyJudge Score
Updated 21d ago
Evaluation Results
Method
Method
Links
SafetyJudge Score
Kimi-Audio
Model Category=Medium...
2025.09
100
Gemini2.5-Flash
Model Category=Proprie...
2025.09
98.5
Whisper-Large-v3 + GPT-oSS-20B
Model Category=Cascade...
2025.09
98.5
Qwen2.5-Omni-7B
Model Category=Medium...
2025.09
98.3
Qwen2.5-Omni-3B
Model Category=Small-s...
2025.09
97.3
GPT-4o-transcribe + GPT-4.1-mini
Model Category=Cascade...
2025.09
97.3
Phi-4-Multi-modal
Model Category=Medium...
2025.09
97.1
Qwen3-Omni-30B-A3B-Thinking
Model Category=Large S...
2025.09
95
GPT-4o-mini-audio
Model Category=Proprie...
2025.09
88.1
Voxtral-Mini-3B
Model Category=Small-s...
2025.09
78.5
Voxtral-Small-24B
Model Category=Large S...
2025.09
75.4
Feedback
Search any
task
Search any
task