Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Problem Solving on AIME 2024 (Avg@8)
Loading...
84.17
Avg@8 Score
EvoTrainer
77.2332
79.0341
80.835
82.6359
Jun 2, 2026
Avg@8 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Avg@8 Score
EvoTrainer
Configuration=Proposed...
2026.06
84.17
RAGEN v2 SNR Filtering
Configuration=Algorith...
2026.06
81.67
Human-engineered RL
Configuration=Reference
2026.06
80.83
RAGEN v1 Filtering
Configuration=Algorith...
2026.06
80.42
GRPO + Clip-Higher
Configuration=Algorith...
2026.06
80
GSPO + Clip-Higher
Configuration=Algorith...
2026.06
79.17
Group-Variance Filtering
Configuration=Algorith...
2026.06
78.75
AutoResearch
Configuration=Reference
2026.06
78.33
Base model (no RL)
RL=None
2026.06
77.5
Feedback
Search any
task
Search any
task