Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Human Preference Evaluation on Arena Creative Writing
Loading...
23.4
Win Rate
JS
4.472
9.386
14.3
19.214
Nov 5, 2025
Win Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Win Rate
JS
Backbone=Llama-3.2-3B-...
2025.11
23.4
RLOO
Backbone=Llama-3.2-3B-...
2025.11
20.2
Llama-3.2-3B-It
2025.11
5.2
Feedback
Search any
task
Search any
task