Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning Evaluation on MATH
Loading...
74.8
Utility
PolicyAlign
70.64
71.72
72.8
73.88
Jun 24, 2026
Utility
Updated 1mo ago
Evaluation Results
Method
Method
Links
Utility
PolicyAlign
Backbone=Qwen3-4B
2026.06
74.8
ICL
Backbone=Qwen3-4B
2026.06
74
Base
Backbone=Qwen3-4B
2026.06
72.8
SFT
Backbone=Qwen3-4B
2026.06
70.8
Feedback
Search any
task
Search any
task