Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on AIME OpenR1-Math Harder 2024
Loading...
72.7
Accuracy
Qwen-4B
61.052
64.076
67.1
70.124
Feb 11, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen-4B
Backbone=Qwen, Paramet...
2026.02
72.7
RePO
Backbone=Qwen, Paramet...
2026.02
72.1
LUFFY
Backbone=Qwen, Paramet...
2026.02
61.5
Feedback
Search any
task
Search any
task
