Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Math Reasoning on AMC (Avg@32, Pass@16)
Loading...
73.64
Avg@32
training-time reweighting
25.8
38.22
50.64
63.06
Mar 23, 2026
Avg@32
Pass@16
Updated 25d ago
Evaluation Results
Method
Method
Links
Avg@32
Pass@16
training-time reweighting
Model=Qwen2.5-Math-7B
2026.03
73.64
89.69
DAPO
Model=Qwen2.5-Math-7B
2026.03
73.04
89.03
training-time reweighting
Model=Qwen3-8B-Base
2026.03
71.05
92.3
DAPO
Model=Qwen3-8B-Base
2026.03
69.13
88.51
Base
Model=Qwen2.5-Math-7B
2026.03
40.62
79.25
Base
Model=Qwen3-8B-Base
2026.03
27.64
78.09
Feedback
Search any
task
Search any
task