Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on AIME 25 (Accuracy (Avg@8))
Loading...
75.7
Accuracy (Avg@8)
CERL full
65.092
67.846
70.6
73.354
May 22, 2026
Accuracy (Avg@8)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy (Avg@8)
CERL full
Training=SFT+RL
2026.05
75.7
Halo
Training=SFT+RL
2026.05
73.2
Fixed-ratio erasure + free answer
Training=None
2026.05
72.2
Base Qwen3-14B
Training=N/A
2026.05
70.5
Length-penalty RL
Training=RL
2026.05
69.4
TokenSkip†
Training=SFT
2026.05
65.5
Feedback
Search any
task
Search any
task