Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Malicious activity detection on ADR-Bench
Loading...
100
Precision
ADR
13.368
35.859
58.35
80.841
May 17, 2026
Precision
Recall
F1 Score
True Positives (TP)
False Positives (FP)
False Positive Rate (FPR)
Cost per Task ($)
Latency (s)
Cost per TP ($)
P95 Latency (s)
Updated 15d ago
Evaluation Results
Method
Method
Links
Precision
Recall
F1 Score
True Positives (TP)
False Positives (FP)
False Positive Rate (FPR)
Cost per Task ($)
Latency (s)
Cost per TP ($)
P95 Latency (s)
ADR
2026.05
100
66.7
80
28
0
0
0.024
18.5
0.26
37.9
ALRPHFS
2026.05
33.3
40.5
36.6
17
34
13
0.001
9.2
0.022
14.8
GuardAgent
2026.05
23.1
21.4
22.2
9
30
11.5
0.012
9.4
0.407
12.5
LlamaFirewall
2026.05
16.7
19
17.8
8
40
15.3
0.459
93.8
17.377
225.7
Feedback
Search any
task
Search any
task