Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Prompt Injection Detection on EIA
Loading...
97.39
Recall
GPT-4.1
4.7052
28.7676
52.83
76.8924
Apr 14, 2026
Recall
Updated 4d ago
Evaluation Results
Method
Method
Links
Recall
GPT-4.1
Model Type=Closed-sour...
2026.04
97.39
WebAgentGuard-4B
Model Type=Ours
2026.04
95.69
WebAgentGuard-8B
Model Type=Ours
2026.04
93.71
GPT-4o
Model Type=Closed-sour...
2026.04
93.07
Prompt-Guard-2-86M
Model Type=Guard models
2026.04
92.79
Qwen3-VL-Instruct-4B
Model Type=Open-source...
2026.04
78.45
GPT-4o-Mini
Model Type=Closed-sour...
2026.04
63.18
GuardReasoner-VL-7B
Model Type=Guard models
2026.04
58.87
Qwen3-VL-Instruct-8B
Model Type=Open-source...
2026.04
44.88
Llama-Guard-3-Vision-11B
Model Type=Guard models
2026.04
21.77
Llama-3.2-Vision-Instruct-11B
Model Type=Open-source...
2026.04
19.93
Prompt-Guard-1-86M
Model Type=Guard models
2026.04
10.81
Qwen2.5-VL-Instruct-7B
Model Type=Open-source...
2026.04
8.27
Feedback
Search any
task
Search any
task