Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety on AgentHarm
Loading...
53.8
Harm Score
Jupiter-N
52.808
59.504
66.2
72.896
Apr 19, 2026
Harm Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Harm Score
Jupiter-N
Reasoning mode=on, Tem...
2026.04
53.8
Nemotron
Reasoning mode=on, Tem...
2026.04
55.4
Jupiter-N
Reasoning mode=off, Te...
2026.04
73.4
Nemotron
Reasoning mode=off, Te...
2026.04
78.6
Feedback
Search any
task
Search any
task
