Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on AIME 2026 (val)
Loading...
70.7
Accuracy
DeepConf
50.94
56.07
61.2
66.33
Jun 7, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
DeepConf
Sample size (N)=32, Ma...
2026.06
70.7
Self-Consistency
Sample size (N)=32, Ma...
2026.06
65.8
iS@1
Sample size (N)=32, Ma...
2026.06
64.2
Self-Certainty
Sample size (N)=32, Ma...
2026.06
51.7
Feedback
Search any
task
Search any
task
