Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Evaluation on BeaverTails (BT)
Loading...
99.1
BT Score
TELLME NT-Xent
56.772
67.761
78.75
89.739
Feb 7, 2025
BT Score
Updated 6d ago
Evaluation Results
Method
Method
Links
BT Score
TELLME NT-Xent
Backbone=Qwen2.5-7B
2025.02
99.1
TELLME NT-Xent
Backbone=Mistral-7B-v0.3
2025.02
99
TELLME
Backbone=Qwen2.5-7B
2025.02
98.7
TELLME NT-Xent
Backbone=Llama-3.1-8B
2025.02
97.1
TELLME
Backbone=Mistral-7B-v0.3
2025.02
96.2
TELLME
Backbone=Llama-3.1-8B
2025.02
95.5
SFT
Backbone=Llama-3.1-8B
2025.02
95
SFT
Backbone=Mistral-7B-v0.3
2025.02
93.7
Origin
Backbone=Qwen2.5-7B
2025.02
92.1
Origin
Backbone=Mistral-7B-v0.3
2025.02
84.3
Origin
Backbone=Llama-3.1-8B
2025.02
83.1
SFT
Backbone=Qwen2.5-7B
2025.02
58.4
Feedback
Search any
task
Search any
task