Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Math Reasoning on AIME 2024 (mean@8, pass@8)
Loading...
28.54
Mean@8 Score
MOPD
6.44
12.1775
17.915
23.6525
May 12, 2026
Mean@8 Score
Pass@8 Score
Updated 21d ago
Evaluation Results
Method
Method
Links
Mean@8 Score
Pass@8 Score
MOPD
Base Model=Qwen3-4B
2026.05
28.54
33.12
GRPO
Base Model=Qwen3-4B
2026.05
17.09
32.05
Qwen3-4B
status=base model
2026.05
16.89
31.6
SDPO
Base Model=Qwen3-4B
2026.05
7.29
16.29
Feedback
Search any
task
Search any
task