Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Harm Classification on Harm-C
Loading...
71.2
Accuracy
MuPHIRM
38.856
47.253
55.65
64.047
May 28, 2026
Accuracy
F1 Score
Updated 5d ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
MuPHIRM
Training Paradigm=GRPO...
2026.05
71.2
71.1
MuPHIRM w/o warmup
Training Paradigm=GRPO...
2026.05
62.7
61
Random
2026.05
50
48.9
Zero-shot + CoT
Training Paradigm=Infe...
2026.05
46.8
44.8
Label + Rationale
Training Paradigm=SFT
2026.05
42.3
38.3
Zero-shot + Decomposition
Training Paradigm=Infe...
2026.05
40.3
35.4
Zero-shot
Training Paradigm=Infe...
2026.05
40.1
34.7
Feedback
Search any
task
Search any
task