Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Risk Assessment on Sens. Risk Person (C)
Loading...
95.4
Score
Qwen3.5-Plus
-3.816
21.942
47.7
73.458
Jun 23, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Qwen3.5-Plus
Model Size=397B
2026.06
95.4
Yuvion VL-32B
Protocol=Instruct
2026.06
94.5
Qwen3-VL-8B
Protocol=Instruct
2026.06
93.1
Qwen3-VL-32B
Protocol=Instruct
2026.06
92.7
Qwen3-VL-32B
Protocol=Thinking
2026.06
92.1
Yuvion VL-8B
Protocol=Instruct
2026.06
91.2
Qwen3-VL-8B
Protocol=Thinking
2026.06
90
Yuvion VL-32B
Protocol=Reasoning
2026.06
89.5
Yuvion VL-8B
Protocol=Reasoning
2026.06
86.7
GPT-5.4
Model Size=≈1.5T
2026.06
85.3
GLM-5
Model Size=≈700B
2026.06
39.4
K2.5
Model Size=≈1T
2026.06
0
Feedback
Search any
task
Search any
task