Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Problem Solving on AIME 2025 (Avg@8)
Loading...
73.33
Avg@8
EvoTrainer
67.2668
68.8409
70.415
71.9891
Jun 2, 2026
Avg@8
Updated 1mo ago
Evaluation Results
Method
Method
Links
Avg@8
EvoTrainer
Configuration=Proposed...
2026.06
73.33
RAGEN v2 SNR Filtering
Configuration=Algorith...
2026.06
72.5
Human-engineered RL
Configuration=Reference
2026.06
71.67
RAGEN v1 Filtering
Configuration=Algorith...
2026.06
70.83
AutoResearch
Configuration=Reference
2026.06
70.42
GSPO + Clip-Higher
Configuration=Algorith...
2026.06
70
GRPO + Clip-Higher
Configuration=Algorith...
2026.06
69.58
Group-Variance Filtering
Configuration=Algorith...
2026.06
68.75
Base model (no RL)
RL=None
2026.06
67.5
Feedback
Search any
task
Search any
task