Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Information Sensitivity Estimation on CONFAIDE Tier 1 (Info-Sensitivity)
Loading...
11.5
Sensitivity
LLaMA3-8B (Drunk language inducement)
-74.82
-52.41
-30
-7.59
Jan 19, 2026
Sensitivity
Updated 3mo ago
Evaluation Results
Method
Method
Links
Sensitivity
LLaMA3-8B (Drunk language inducement)
Variant=Pr.
2026.01
11.5
Mistral-7B (Drunk language inducement)
Variant=RL
2026.01
5
LLaMA3-8B (Drunk language inducement)
Variant=FT
2026.01
0.5
LLaMA3-8B (Drunk language inducement)
Variant=RL
2026.01
-14.5
Mistral-7B (Drunk language inducement)
Variant=FT
2026.01
-25
LLaMA2-7B (Drunk language inducement)
Variant=RL
2026.01
-29.5
LLaMA2-7B (Drunk language inducement)
Variant=FT
2026.01
-30.5
LLaMA2-7B (Drunk language inducement)
Variant=Pr.
2026.01
-33.5
LLaMA3-8B
Variant=Base
2026.01
-33.5
GPT-3.5 (Drunk language inducement)
Variant=Pr.
2026.01
-42
GPT-4 (Drunk language inducement)
Variant=FT
2026.01
-49
LLaMA2-7B
Variant=Base
2026.01
-55.5
Mistral-7B (Drunk language inducement)
Variant=Pr.
2026.01
-60
Mistral-7B
Variant=Base
2026.01
-65
GPT-4 (Drunk language inducement)
Variant=Pr.
2026.01
-67
GPT-3.5
Variant=Base
2026.01
-70
GPT-4
Variant=Base
2026.01
-71.5
Feedback
Search any
task
Search any
task