Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Math Reasoning on OlympiadBench (Pass@1, AES)
Loading...
48.19
Pass@1
SAS
44.55
45.495
46.44
47.385
Apr 27, 2026
Pass@1
AES
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1
AES
SAS
#Tok=3008
2026.04
48.19
-
LAPO-I
#Tok=3735
2026.04
48.18
-
ThinkPrune-4k
#Tok=3651
2026.04
47.62
-
DeepScaleR
#Tok=4824
2026.04
47.23
-
GRPO-4K
#Tok=3411
2026.04
47.09
-
L1-Max
#Tok=1703
2026.04
44.69
-
Feedback
Search any
task
Search any
task