Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Safety Evaluation on SafetyBench (test)
Loading...
81.321
Accuracy
AWQ-trust
66.03196
70.00123
73.9705
77.93977
Jan 17, 2026
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
AWQ-trust
Backbone=Qwen-2.5-7B-I...
2026.01
81.321
Full Precision
Backbone=Qwen-2.5-7B-I...
2026.01
80.394
AWQ
Backbone=Qwen-2.5-7B-I...
2026.01
80.017
Full Precision
Backbone=Llama-3.1-8B-...
2026.01
76.502
AWQ
Backbone=Llama-3.1-8B-...
2026.01
75.864
AWQ-trust
Backbone=Llama-3.1-8B-...
2026.01
75.68
AWQ-trust
Backbone=Gemma-7B-Inst...
2026.01
66.734
AWQ
Backbone=Gemma-7B-Inst...
2026.01
66.672
Full Precision
Backbone=Gemma-7B-Inst...
2026.01
66.62
Feedback
Search any
task
Search any
task