Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Human Evaluation on Skywork (test)
Loading...
1,610.1
Elo Rating
AAD
1,408.444
1,460.797
1,513.15
1,565.503
Sep 30, 2025
Elo Rating
AAD Win Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Elo Rating
AAD Win Rate
AAD
Backbone=3B LLaMA
2025.09
1,610.1
-
Greedy DPO
Backbone=3B LLaMA
2025.09
1,524.4
58.7
EFT
Backbone=3B LLaMA
2025.09
1,513.2
70.8
Greedy SFT
Backbone=3B LLaMA
2025.09
1,436.2
71.7
Bo2
Backbone=3B LLaMA
2025.09
1,416.2
73.5
Feedback
Search any
task
Search any
task