Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Math Reasoning on AIME 2025 (Pass@1, AES)
Loading...
27.92
Pass@1
LAPO-I
21.42
23.1075
24.795
26.4825
Apr 27, 2026
Pass@1
AES
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1
AES
LAPO-I
#Tok=5290
2026.04
27.92
-
DeepScaleR
#Tok=6444
2026.04
26.88
-
ThinkPrune-4k
#Tok=5177
2026.04
26.67
-
SAS
#Tok=4295
2026.04
26.67
-
GRPO-4K
#Tok=4812
2026.04
25.42
-
L1-Max
#Tok=2032
2026.04
21.67
-
Feedback
Search any
task
Search any
task