Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Operational Triage on CIFAR-10 (test)
Loading...
10,000
Average Samples
Cohen-10k (Ref)
338.92
2,847.085
5,355.25
7,863.415
Jun 26, 2026
Average Samples
Average Samples in Bin A
Success Rate
Definitive Rate
Updated 27d ago
Evaluation Results
Method
Method
Links
Average Samples
Average Samples in Bin A
Success Rate
Definitive Rate
Cohen-10k (Ref)
Sigma=1.0, N=3000
2026.06
10,000
10,000
100
100
KT Prior (Fixed)
Sigma=1.0, N=3000
2026.06
1,733.2
948.8
100
90.8
Tiered Spec Race
Sigma=1.0, N=3000
2026.06
1,448.8
988.4
99.9
92.5
Relaxed Tiered Cascade
Sigma=1.0, N=3000
2026.06
710.5
480
99.9
92.5
Feedback
Search any
task
Search any
task