Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Value Alignment on Harmlessness 4
Loading...
4.305
Conformity Score
PICACO
2.42156
2.91053
3.3995
3.88847
Jul 22, 2025
Conformity Score
Updated 7d ago
Evaluation Results
Method
Method
Links
Conformity Score
PICACO
Target Model=Gemini-1....
2025.07
4.305
URIAL
Target Model=Gemini-1....
2025.07
4.245
OPRO
Target Model=Gemini-1....
2025.07
4.215
PICACO
2025.07
4.173
URIAL+SUM
Target Model=Gemini-1....
2025.07
4.086
Q+IF
Model=GPT-4o-mini
2025.07
4.083
Q+IF
Training=SFT
2025.07
4.081
Q+IF+COT
Target Model=Gemini-1....
2025.07
4.038
Q+IF
2025.07
4.032
MODULAR
Target Model=Gemini-1....
2025.07
4.029
MP+SYSTEM 2
Target Model=Gemini-1....
2025.07
3.907
Q
Target Model=Gemini-1....
2025.07
3.884
Q+IF
Target Model=Gemini-1....
2025.07
3.869
MP+SYSTEM 1
Target Model=Gemini-1....
2025.07
3.774
Q+IF
Training=SFT+
2025.07
3.266
URIAL
Training=SFT
2025.07
2.494
Feedback
Search any
task
Search any
task