Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Harm Detection on Harm-P
Loading...
59.2
Macro-F1
MuPHIRM
31.744
38.872
46
53.128
May 28, 2026
Macro-F1
Updated 5d ago
Evaluation Results
Method
Method
Links
Macro-F1
MuPHIRM
Source Dataset=MuPHI
2026.05
59.2
Label-tuned
Source Dataset=MuPHI
2026.05
58.4
MuPHIRM
Source Dataset=Harm-C
2026.05
58.2
MuPHIRM
Source Dataset=FHM
2026.05
55.2
Label-tuned
Source Dataset=FHM
2026.05
48.3
Label-tuned
Source Dataset=Harm-C
2026.05
32.8
Feedback
Search any
task
Search any
task