Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Preference Classification on Math Reasoning (test)
Loading...
85.4
Classification Accuracy
BTPO
52.432
60.991
69.55
78.109
Oct 17, 2025
Classification Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Classification Accuracy
BTPO
Backbone=Qwen2.5-7B-In...
2025.10
85.4
RM-R1-finetuned
Backbone=Qwen2.5-7B-In...
2025.10
55.9
RM-R1
Backbone=Qwen2.5-7B-In...
2025.10
55
GRPO (pair)
Backbone=Qwen2.5-7B-In...
2025.10
53.7
Feedback
Search any
task
Search any
task