Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Tone (multi-class) on Representative guardrail dataset
Loading...
92
F1 Score
Luna-2
64.96
71.98
79
86.02
Feb 20, 2026
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
Luna-2
Model=Llama 3.2 3B
2026.02
92
ChainPoll
Model=GPT 4.1
2026.02
90
Single token
Model=Llama 3.2 3B
2026.02
66
Feedback
Search any
task
Search any
task
