Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Ethical alignment evaluation on Open-ended ethical scenarios 20 countries 310 scenarios each
Loading...
52.1
MIS
Vanilla
29.324
35.237
41.15
47.063
May 11, 2026
MIS
Delta % Change
Updated 21d ago
Evaluation Results
Method
Method
Links
MIS
Delta % Change
Vanilla
Backbone=Phi-3.5-mini,...
2026.05
52.1
-
DISCA
Backbone=Phi-3.5-mini,...
2026.05
51
2.13
Vanilla
Backbone=Llama-3.3-70B...
2026.05
47.1
-
DISCA
Backbone=Llama-3.3-70B...
2026.05
43.9
6.85
Vanilla
Backbone=Phi-4 (14B),...
2026.05
32.4
-
Vanilla
Backbone=Qwen2.5-7B, D...
2026.05
32.1
-
DISCA
Backbone=Qwen2.5-7B, D...
2026.05
30.6
4.55
DISCA
Backbone=Phi-4 (14B),...
2026.05
30.2
6.67
Feedback
Search any
task
Search any
task