Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Stereotypical Bias Evaluation on CrowS-Pairs (CP)
Loading...
64.7
CP Accuracy
COFT
58.46
60.08
61.7
63.32
May 28, 2026
CP Accuracy
Average Rank (CP)
Updated 2d ago
Evaluation Results
Method
Method
Links
CP Accuracy
Average Rank (CP)
COFT
Backbone=Mistral-7B-In...
2026.05
64.7
1
COFT
Backbone=LLaMA-2-13B
2026.05
63.5
1
DT-CD⋆
Backbone=Mistral-7B-In...
2026.05
62.4
2.6
DExperts
Backbone=Mistral-7B-In...
2026.05
62.1
3.1
DT-CD⋆
Backbone=LLaMA-2-13B
2026.05
61.3
2.8
SDD
Backbone=Mistral-7B-In...
2026.05
61.2
3.9
DExperts
Backbone=LLaMA-2-13B
2026.05
61
3.3
SDD
Backbone=LLaMA-2-13B
2026.05
60.1
4
Vanilla
Backbone=Mistral-7B-In...
2026.05
59.8
5.8
Vanilla
Backbone=LLaMA-2-13B
2026.05
58.7
5.8
Feedback
Search any
task
Search any
task