Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Preference Classification on Instruction Following (IF) (test)
Loading...
61.4
Accuracy
BTPO
51.832
54.316
56.8
59.284
Oct 17, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
BTPO
Backbone=Qwen2.5-7B-In...
2025.10
61.4
RM-R1
Backbone=Qwen2.5-7B-In...
2025.10
52.2
RM-R1-finetuned
Backbone=Qwen2.5-7B-In...
2025.10
52.2
GRPO (pair)
Backbone=Qwen2.5-7B-In...
2025.10
52.2
Feedback
Search any
task
Search any
task