Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Prompt Injection Detection on AgentDojo
Loading...
97
Banking RL
RedVisorLlama
7.56
30.78
54
77.22
Feb 2, 2026
Banking RL
Banking ES
Travel RL
Travel ES
Slack RL
Slack ES
Workspace RL
Workspace ES
Updated 4d ago
Evaluation Results
Method
Method
Links
Banking RL
Banking ES
Travel RL
Travel ES
Slack RL
Slack ES
Workspace RL
Workspace ES
RedVisorLlama
Backbone=Llama-3-8B, A...
2026.02
97
97
90
90
88
89
89
91
PromptLocate
Attack Type=Important...
2026.02
96
97
87
89
81
84
86
91
RedVisorQwen
Backbone=Qwen-2.5-7B,...
2026.02
95
96
86
89
80
81
84
87
RedVisorMist
Backbone=Mistral-7B, A...
2026.02
94
95
83
85
78
80
82
85
PromptArmor
Attack Type=Important...
2026.02
11
15
8
10
6
7
9
11
Feedback
Search any
task
Search any
task