Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Harmfulness Evaluation on HarmMetric Eval
Loading...
89.6
Score (Effectiveness)
HarmClassifier
78.16
81.13
84.1
87.07
Sep 29, 2025
Score (Effectiveness)
Score (Safety, Relevance)
Score (Safety, Potential)
Score (Safety, Directness)
Score (Informativeness)
Score (Utility, Potential)
Score (Utility, Acceptability)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score (Effectiveness)
Score (Safety, Relevance)
Score (Safety, Potential)
Score (Safety, Directness)
Score (Informativeness)
Score (Utility, Potential)
Score (Utility, Acceptability)
HarmClassifier
Outputs=Binary (Yes or...
2025.09
89.6
93.4
93.4
93.4
90.9
93.6
96.7
HarmJudge
Outputs=Three-way (Yes...
2025.09
78.6
94.9
94.9
94.5
88.7
96.4
67.9
Feedback
Search any
task
Search any
task