Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Evaluation on StrongReject SB
Loading...
99.1
SB Score
TELLME NT-Xent
67.588
75.769
83.95
92.131
Feb 7, 2025
SB Score
Updated 6d ago
Evaluation Results
Method
Method
Links
SB Score
TELLME NT-Xent
Backbone=Qwen2.5-7B
2025.02
99.1
TELLME NT-Xent
Backbone=Llama-3.1-8B
2025.02
98.9
TELLME
Backbone=Qwen2.5-7B
2025.02
98.3
TELLME NT-Xent
Backbone=Mistral-7B-v0.3
2025.02
96.8
TELLME
Backbone=Llama-3.1-8B
2025.02
96.6
SFT
Backbone=Llama-3.1-8B
2025.02
95.7
Origin
Backbone=Qwen2.5-7B
2025.02
94.6
SFT
Backbone=Mistral-7B-v0.3
2025.02
94.3
Origin
Backbone=Llama-3.1-8B
2025.02
94.2
TELLME
Backbone=Mistral-7B-v0.3
2025.02
88.3
Origin
Backbone=Mistral-7B-v0.3
2025.02
76.5
SFT
Backbone=Qwen2.5-7B
2025.02
68.8
Feedback
Search any
task
Search any
task