Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on AIME 25 (pass@1, pass@64)
Loading...
44
Pass@1
DPólya
25.28
30.14
35
39.86
May 8, 2026
Pass@1
Pass@64
Updated 22d ago
Evaluation Results
Method
Method
Links
Pass@1
Pass@64
DPólya
n=64
2026.05
44
18.66
DPólya
n=2
2026.05
40
17.44
DPólya
n=16
2026.05
40
17.52
DPólya
n=32
2026.05
40
16.97
DPólya
n=1
2026.05
38
16.71
DPólya
n=4
2026.05
37
16.7
DPólya
n=8
2026.05
34
15.26
DSTaR
n=N/A
2026.05
33
13.91
Zero-Shot
n=N/A
2026.05
26
12.84
Feedback
Search any
task
Search any
task