List your company

Preference Classification on Math Reasoning (test)

85.4Classification AccuracyBTPO
52.43260.99169.5578.109Oct 17, 2025

Evaluation results

MethodLinks
BTPOBackbone=Qwen2.5-7B-Instruct2025.1085.4
RM-R1-finetunedBackbone=Qwen2.5-7B-Instruct, Fine-tuned=true2025.1055.9
RM-R1Backbone=Qwen2.5-7B-Instruct2025.1055
GRPO (pair)Backbone=Qwen2.5-7B-Instruct2025.1053.7