Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Fairness Evaluation on Jigsaw
Loading...
75.6
BiasAUC
AWQ-trust
39.824
49.112
58.4
67.688
Jan 17, 2026
BiasAUC
FinalAUC
Updated 4d ago
Evaluation Results
Method
Method
Links
BiasAUC
FinalAUC
AWQ-trust
Model=Qwen-2.5-7B-Inst...
2026.01
75.6
75.8
AWQ-trust
Model=Llama-3.1-8B-Ins...
2026.01
74.3
74.5
Full Precision
Model=Qwen-2.5-7B-Inst...
2026.01
74.2
74.4
AWQ
Model=Qwen-2.5-7B-Inst...
2026.01
74.1
74.4
Full Precision
Model=Llama-3.1-8B-Ins...
2026.01
73.9
74.1
AWQ
Model=Llama-3.1-8B-Ins...
2026.01
73.2
73.4
Full Precision
Model=Gemma-7B-Instruc...
2026.01
48.7
49
AWQ-trust
Model=Gemma-7B-Instruc...
2026.01
47.7
48.1
AWQ
Model=Gemma-7B-Instruc...
2026.01
41.2
41.7
Feedback
Search any
task
Search any
task