Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Prompt Injection Attack on Tool-Completion (TCA)
Loading...
0.12
ASR
CAHL
0.0848
0.3224
0.56
0.7976
Dec 3, 2025
ASR
Updated 4d ago
Evaluation Results
Method
Method
Links
ASR
CAHL
2025.12
0.12
Llama-3.1-8B-Instruct
2025.12
0.24
CAHL
2025.12
0.45
ISE
2025.12
0.47
Delimiter
2025.12
0.57
ISE
2025.12
0.58
Llama-3.1-8B-Instruct
2025.12
0.61
GPT-4o
2025.12
0.79
Delimiter
2025.12
0.86
GPT-4o
2025.12
0.91
DeepSeek-R1
2025.12
0.92
o3-mini
2025.12
0.99
DeepSeek-R1
2025.12
0.99
o3-mini
2025.12
1
Feedback
Search any
task
Search any
task