Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Problem Solving on CNMO 2024 (Avg@8)
Loading...
81.94
Avg@8
EvoTrainer
74.7224
76.5962
78.47
80.3438
Jun 2, 2026
Avg@8
Updated 1mo ago
Evaluation Results
Method
Method
Links
Avg@8
EvoTrainer
Configuration=Proposed...
2026.06
81.94
RAGEN v2 SNR Filtering
Configuration=Algorith...
2026.06
80.56
GRPO + Clip-Higher
Configuration=Algorith...
2026.06
79.17
AutoResearch
Configuration=Reference
2026.06
78.47
Human-engineered RL
Configuration=Reference
2026.06
77.78
RAGEN v1 Filtering
Configuration=Algorith...
2026.06
77.78
GSPO + Clip-Higher
Configuration=Algorith...
2026.06
76.39
Group-Variance Filtering
Configuration=Algorith...
2026.06
76.39
Base model (no RL)
RL=None
2026.06
75
Feedback
Search any
task
Search any
task