Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Reasoning on AIME 25 (Score)
Loading...
12.6
AIME Score
MathForge
4.4776
6.5863
8.695
10.8037
Jan 28, 2026
AIME Score
Updated 4d ago
Evaluation Results
Method
Method
Links
AIME Score
MathForge
Backbone=Qwen2.5-Math-...
2026.01
12.6
MQR
Backbone=Qwen2.5-Math-...
2026.01
11.77
DGPO
Backbone=Qwen2.5-Math-...
2026.01
10.21
GRPO-AD
Backbone=Qwen2.5-Math-...
2026.01
9.48
GPG
Backbone=Qwen2.5-Math-...
2026.01
9.06
DAPO
Backbone=Qwen2.5-Math-...
2026.01
8.75
GRPO
Backbone=Qwen2.5-Math-...
2026.01
8.44
GSPO
Backbone=Qwen2.5-Math-...
2026.01
8.33
Dr.GRPO
Backbone=Qwen2.5-Math-...
2026.01
8.23
Base Model
Backbone=Qwen2.5-Math-...
2026.01
4.79
Feedback
Search any
task
Search any
task