Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Prompt Injection Attack on Tool-Completion Naive-e
Loading...
15
ASR
CAHL
11.6
34.55
57.5
80.45
Dec 3, 2025
ASR
Updated 4d ago
Evaluation Results
Method
Method
Links
ASR
CAHL
2025.12
15
ISE
2025.12
33
Llama-3.1-8B-Instruct
2025.12
90
o3-mini
2025.12
95
Delimiter
2025.12
99
GPT-4o
2025.12
100
DeepSeek-R1
2025.12
100
Feedback
Search any
task
Search any
task