Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Instruction Following on AlpacaEval (OOD)
Loading...
24.9
KL Div (α=1)
GEB-arctanh(π − 1)
24.7652
25.6751
26.585
27.4949
Sep 27, 2025
KL Div (α=1)
Hellinger Dist (α=0.5)
f-KL Div (α=0)
Average Divergence
Updated 4d ago
Evaluation Results
Method
Method
Links
KL Div (α=1)
Hellinger Dist (α=0.5)
f-KL Div (α=0)
Average Divergence
GEB-arctanh(π − 1)
Backbone=LLaMA-3-8B-SF...
2025.09
24.9
25.96
19.62
23.49
f-DPO
Backbone=LLaMA-3-8B-SF...
2025.09
25.72
24.73
17.8
22.75
FEB
Backbone=LLaMA-3-8B-SF...
2025.09
25.72
23.75
19.62
23.03
GEB-1/π
Backbone=LLaMA-3-8B-SF...
2025.09
26.1
25.28
19.8
23.73
GEB-π
Backbone=LLaMA-3-8B-SF...
2025.09
28.27
25.87
20.05
24.73
Feedback
Search any
task
Search any
task