Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Harm Detection on MuPHI
Loading...
85.4
Macro-F1
MuPHIRM
31.216
45.283
59.35
73.417
May 28, 2026
Macro-F1
Updated 5d ago
Evaluation Results
Method
Method
Links
Macro-F1
MuPHIRM
Source Dataset=Harm-C
2026.05
85.4
MuPHIRM
Source Dataset=Harm-P
2026.05
81.2
Label-tuned
Source Dataset=FHM
2026.05
79.8
Label-tuned
Source Dataset=Harm-P
2026.05
79.2
MuPHIRM
Source Dataset=FHM
2026.05
56.4
Label-tuned
Source Dataset=Harm-C
2026.05
33.3
Feedback
Search any
task
Search any
task