Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on AIME 2024 & 2025 (AUROC)
Loading...
94.1
AUROC
SCVC
65.292
72.771
80.25
87.729
Mar 19, 2026
AUROC
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUROC
SCVC
Sampling budget (K)=8
2026.03
94.1
SCVC
Sampling budget (K)=5
2026.03
91.9
SC
Sampling budget (K)=8
2026.03
90
SCVC
Sampling budget (K)=2
2026.03
89.5
SC
Sampling budget (K)=5
2026.03
85.9
SC
Sampling budget (K)=2
2026.03
82.6
VC
Sampling budget (K)=8
2026.03
81.7
VC
Sampling budget (K)=5
2026.03
78.8
VC
Sampling budget (K)=2
2026.03
67.2
VC
Sampling budget (K)=1
2026.03
66.4
Feedback
Search any
task
Search any
task
