Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Bias QA on BBQ Ambig
Loading...
85.04
Accuracy
CRL-Token
59.1752
65.8901
72.605
79.3199
Feb 11, 2026
Accuracy
Gain
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Gain
CRL-Token
Backbone=LLaMA-3.1 8B,...
2026.02
85.04
1.07
LLaMA-3.1 8B
Evaluation Protocol=1-...
2026.02
83.97
-
CRL-Token
Backbone=Gemma 2 2B, I...
2026.02
65.86
5.69
Gemma 2 2B
Backbone=Gemma 2 2B
2026.02
60.17
-
Feedback
Search any
task
Search any
task