Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Harm Detection on Harm-C
Loading...
60.9
Macro-F1
MuPHIRM
55.076
56.588
58.1
59.612
May 28, 2026
Macro-F1
Updated 5d ago
Evaluation Results
Method
Method
Links
Macro-F1
MuPHIRM
Source Dataset=FHM
2026.05
60.9
MuPHIRM
Source Dataset=Harm-P
2026.05
58.8
MuPHIRM
Source Dataset=MuPHI
2026.05
58.5
Label-tuned
Source Dataset=FHM
2026.05
56.8
Label-tuned
Source Dataset=Harm-P
2026.05
55.5
Label-tuned
Source Dataset=MuPHI
2026.05
55.3
Feedback
Search any
task
Search any
task