Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on AIME 2024 (Score, Best Score, ΔH)
Loading...
0.47
Score
RLOO
0.4284
0.4392
0.45
0.4608
Mar 12, 2026
Score
Best Score
ΔH
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Best Score
ΔH
RLOO
Base Model=Qwen-3-8B,...
2026.03
0.47
0.48
-0.04
GRPO
Base Model=Qwen-3-8B,...
2026.03
0.45
0.47
-0.07
REPO-R
Base Model=Qwen-3-8B,...
2026.03
0.45
0.46
0.13
GSPO
Base Model=Qwen-3-8B,...
2026.03
0.43
0.47
0.05
DAPO
Base Model=Qwen-3-8B,...
2026.03
0.43
0.44
0.23
ADAPO
Base Model=Qwen-3-8B,...
2026.03
0.43
0.43
0.13
Feedback
Search any
task
Search any
task
