Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Auditing on Llama-3.2-11B-Vision-Instruct (test)
Loading...
41.85
Detoxify Score
RedDiff w/ alignment (L)
13.9468
21.1909
28.435
35.6791
Mar 8, 2025
Detoxify Score
Perspective API Score
Updated 2mo ago
Evaluation Results
Method
Method
Links
Detoxify Score
Perspective API Score
RedDiff w/ alignment (L)
Modality=Multimodal, A...
2025.03
41.85
45.24
RedDiff w/ alignment (M)
Modality=Multimodal, A...
2025.03
41.81
44.37
RedDiff w/ alignment (H)
Modality=Multimodal, A...
2025.03
41.15
43.78
RedDiff w/o alignment
Modality=Multimodal, A...
2025.03
41.01
43.9
Text-only Baseline
Modality=Text-only
2025.03
15.02
18.68
Feedback
Search any
task
Search any
task