Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Evaluation on DRA
Loading...
92.31
Safety Score
REFLECTOR (+GDPO)
5.3036
27.8918
50.48
73.0682
May 20, 2026
Safety Score
Updated 13d ago
Evaluation Results
Method
Method
Links
Safety Score
REFLECTOR (+GDPO)
Backbone=Llama-3.1-8B-...
2026.05
92.31
REFLECTOR (+GDPO)
Backbone=Qwen-2.5-7B-I...
2026.05
90.38
REFLECTOR (SFT)
Backbone=Qwen-2.5-7B-I...
2026.05
89.46
REFLECTOR (+SFT)
Backbone=Llama-3.1-8B-...
2026.05
88.16
STAIR
Backbone=Qwen-2.5-7B-I...
2026.05
59.81
STAIR
Backbone=Llama-3.1-8B-...
2026.05
55.83
Shallow-Align
Backbone=Qwen-2.5-7B-I...
2026.05
53.2
Shallow-Align
Backbone=Llama-3.1-8B-...
2026.05
48.9
Self-Critique
Backbone=Qwen-2.5-7B-I...
2026.05
17.69
DPO
Backbone=Qwen-2.5-7B-I...
2026.05
15.11
Self-Critique
Backbone=Llama-3.1-8B-...
2026.05
15
DPO
Backbone=Llama-3.1-8B-...
2026.05
13.3
SFT
Backbone=Llama-3.1-8B-...
2026.05
12.5
Original
Backbone=Llama-3.1-8B-...
2026.05
10.04
SFT
Backbone=Qwen-2.5-7B-I...
2026.05
9.62
Original
Backbone=Qwen-2.5-7B-I...
2026.05
8.65
Feedback
Search any
task
Search any
task