Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Harm classification on MuPHI
Loading...
90.3
Accuracy
MuPHIRM
48.388
59.269
70.15
81.031
May 28, 2026
Accuracy
F1 Score
Updated 5d ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
MuPHIRM
Training Paradigm=GRPO...
2026.05
90.3
90.2
MuPHIRM w/o warmup
Training Paradigm=GRPO...
2026.05
79.5
79.5
Label + Rationale
Training Paradigm=SFT
2026.05
78.5
78.4
Zero-shot + Decomposition
Training Paradigm=Infe...
2026.05
76
75.6
Zero-shot + CoT
Training Paradigm=Infe...
2026.05
59.4
53.9
Zero-shot
Training Paradigm=Infe...
2026.05
54.2
47.6
Random
2026.05
50
50
Feedback
Search any
task
Search any
task