Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on AIME24 (mean@8)
Loading...
39.79
Mean@8 Score
ACPO
21.9124
26.5537
31.195
35.8363
Jul 3, 2026
Mean@8 Score
Updated 18d ago
Evaluation Results
Method
Method
Links
Mean@8 Score
ACPO
Model=DeepSeek-R1-Dist...
2026.07
39.79
SAPO
Model=DeepSeek-R1-Dist...
2026.07
38.54
ACPO
Model=Qwen2.5-Math-7B
2026.07
36.56
GTPO
Model=DeepSeek-R1-Dist...
2026.07
36.37
GTPO
Model=Qwen2.5-Math-7B
2026.07
33.97
SAPO
Model=Qwen2.5-Math-7B
2026.07
32.29
80/20
Model=DeepSeek-R1-Dist...
2026.07
32.16
ACPO
Model=Qwen3-8B-Base
2026.07
30.31
80/20
Model=Qwen2.5-Math-7B
2026.07
29.25
SAPO
Model=Qwen3-8B-Base
2026.07
29.06
DAPO
Model=DeepSeek-R1-Dist...
2026.07
29.06
GRPO
Model=DeepSeek-R1-Dist...
2026.07
28.43
DAPO
Model=Qwen2.5-Math-7B
2026.07
27.7
GTPO
Model=Qwen3-8B-Base
2026.07
27.21
GRPO
Model=Qwen2.5-Math-7B
2026.07
26.25
80/20
Model=Qwen3-8B-Base
2026.07
26.02
DAPO
Model=Qwen3-8B-Base
2026.07
24.89
GRPO
Model=Qwen3-8B-Base
2026.07
22.6
Feedback
Search any
task
Search any
task