Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Content Moderation on In-house multimodal moderation data S.S.
Loading...
74
Misrepresentative F1
Human Policy
69.944
70.997
72.05
73.103
Apr 1, 2026
Misrepresentative F1
Finance Claims F1
Exploitative F1
Offensive F1
Updated 16d ago
Evaluation Results
Method
Method
Links
Misrepresentative F1
Finance Claims F1
Exploitative F1
Offensive F1
Human Policy
2026.04
74
83.3
92
89.3
DPR
2026.04
72.7
59.7
90.8
78.6
No Policy
2026.04
71.4
50
79.3
71.4
Seed Information
2026.04
70.1
55.3
83.9
67.9
DPR + Summary
Compressed=true
2026.04
70.1
58.8
87.4
82.1
Feedback
Search any
task
Search any
task