Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Safety on MMDS-Q
Loading...
99.13
F1 Score
LLaVAShield
34.8476
51.5363
68.225
84.9137
Jun 22, 2026
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
LLaVAShield
Category=Open-Source M...
2026.06
99.13
SingGuard-8B
Category=Our Models
2026.06
98.51
SingGuard-2B
Category=Our Models
2026.06
96.97
SingGuard-4B
Category=Our Models
2026.06
96.05
GPT-5.1
Category=Closed-Source...
2026.06
80.28
Qwen3-VL-235B
Category=Open-Source M...
2026.06
72
LlavaGuard
Category=Open-Source M...
2026.06
68
Gemini3-Pro
Category=Closed-Source...
2026.06
67.19
ShieldGemma-2
Category=Open-Source M...
2026.06
64.42
Qwen3-VL-8B
Category=Open-Source M...
2026.06
57.74
GuardReasoner-VL-7B
Category=Open-Source M...
2026.06
56.54
LlamaGuard3-Vision-11B
Category=Open-Source M...
2026.06
55.46
SafeGuard-VL
Category=Open-Source M...
2026.06
47.56
Qwen3-VL-4B
Category=Open-Source M...
2026.06
45.45
LlamaGuard4
Category=Open-Source M...
2026.06
37.32
Feedback
Search any
task
Search any
task