Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Top-N Saturation on Tool selection benchmark
Loading...
20
Certified Upper Bound (pu)
None
19
25.75
32.5
39.25
Oct 5, 2025
Certified Upper Bound (pu)
Updated 2mo ago
Evaluation Results
Method
Method
Links
Certified Upper Bound (pu)
None
Mitigation=None, Selec...
2025.10
20
Anomaly mon.
Mitigation=Anomaly mon...
2025.10
24
StruQ
Mitigation=StruQ, Sele...
2025.10
27
SecAlign
Mitigation=SecAlign, S...
2025.10
33
Perplexity
Mitigation=Perplexity,...
2025.10
39
Defended retr.
Mitigation=Defended re...
2025.10
45
Feedback
Search any
task
Search any
task