Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Context-window selection on PDEBench 8 families (aggregate)
Loading...
67.8
Exact Accuracy
SAKE
10.288
25.219
40.15
55.081
Mar 26, 2026
Exact Accuracy
Within-1 Accuracy
Mean Regret (Knee)
Mean Unique Length Evaluation
Cost Ratio
Updated 4mo ago
Evaluation Results
Method
Method
Links
Exact Accuracy
Within-1 Accuracy
Mean Regret (Knee)
Mean Unique Length Evaluation
Cost Ratio
SAKE
Candidate grid=L = {1,...
2026.03
67.8
91.7
6.1
5.3
0.051
ASHA
Candidate grid=L = {1,...
2026.03
57.3
88
8
9.6
0.092
Direct-4-Shortlist
Candidate grid=L = {1,...
2026.03
50
84.4
9.4
7.3
0.072
System-core
Candidate grid=L = {1,...
2026.03
12.5
40.6
28
0
0
Feedback
Search any
task
Search any
task