Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Math Reasoning on AIME 24 (Avg@32, Pass@16)
Loading...
39.06
Avg@32 Score
training-time reweighting
4.0744
13.1572
22.24
31.3228
Mar 23, 2026
Avg@32 Score
Pass Rate (@16)
Updated 25d ago
Evaluation Results
Method
Method
Links
Avg@32 Score
Pass Rate (@16)
training-time reweighting
Model=Qwen2.5-Math-7B
2026.03
39.06
60.58
training-time reweighting
Model=Qwen3-8B-Base
2026.03
38.13
69.87
DAPO
Model=Qwen3-8B-Base
2026.03
36.98
72.3
DAPO
Model=Qwen2.5-Math-7B
2026.03
35.73
54.09
Base
Model=Qwen2.5-Math-7B
2026.03
14.79
47.46
Base
Model=Qwen3-8B-Base
2026.03
5.42
30.63
Feedback
Search any
task
Search any
task