Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Bias Evaluation on WinoGender
Loading...
0.068
EBS
Default
0.03196
0.27523
0.5185
0.76177
Oct 29, 2024
EBS
Updated 4d ago
Evaluation Results
Method
Method
Links
EBS
Default
Backbone=GPT-2 XL
2024.10
0.068
ATLAS
Backbone=GPT-2 XL
2024.10
0.153
Default
Backbone=LLAMA 3
2024.10
0.255
Default
Backbone=GPT-J
2024.10
0.37
ATLAS
Backbone=LLAMA 3
2024.10
0.409
Default
Backbone=LLAMA 2
2024.10
0.728
ATLAS
Backbone=LLAMA 2
2024.10
0.815
ATLAS
Backbone=GPT-J
2024.10
0.969
Feedback
Search any
task
Search any
task