Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Evaluation on Xs (test)
Loading...
100
Safety Score
REFLECTOR (+SFT)
68.28
76.515
84.75
92.985
May 20, 2026
Safety Score
Updated 13d ago
Evaluation Results
Method
Method
Links
Safety Score
REFLECTOR (+SFT)
Backbone=Llama-3.1-8B-...
2026.05
100
REFLECTOR (+GDPO)
Backbone=Llama-3.1-8B-...
2026.05
100
REFLECTOR (SFT)
Backbone=Qwen-2.5-7B-I...
2026.05
100
REFLECTOR (+GDPO)
Backbone=Qwen-2.5-7B-I...
2026.05
100
STAIR
Backbone=Llama-3.1-8B-...
2026.05
99
STAIR
Backbone=Qwen-2.5-7B-I...
2026.05
99
Shallow-Align
Backbone=Llama-3.1-8B-...
2026.05
96.5
Shallow-Align
Backbone=Qwen-2.5-7B-I...
2026.05
96
SFT
Backbone=Llama-3.1-8B-...
2026.05
94.5
Self-Critique
Backbone=Llama-3.1-8B-...
2026.05
88.5
Original
Backbone=Llama-3.1-8B-...
2026.05
88
DPO
Backbone=Llama-3.1-8B-...
2026.05
86
SFT
Backbone=Qwen-2.5-7B-I...
2026.05
84.5
Self-Critique
Backbone=Qwen-2.5-7B-I...
2026.05
75.25
Original
Backbone=Qwen-2.5-7B-I...
2026.05
73.5
DPO
Backbone=Qwen-2.5-7B-I...
2026.05
69.5
Feedback
Search any
task
Search any
task