Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Indirect Prompt Injection on LivePI Group chat (n=15)
Loading...
100
ASR
GPT-5.3-Codex
95
97.5
100
102.5
May 18, 2026
ASR
Updated 15d ago
Evaluation Results
Method
Method
Links
ASR
GPT-5.3-Codex
Model Type=Base LLM
2026.05
100
Claude Opus 4.6
Model Type=Base LLM
2026.05
100
Gemini 3.1 Pro
Model Type=Base LLM
2026.05
100
Kimi K2.5
Model Type=Base LLM
2026.05
100
GLM-5
Model Type=Base LLM
2026.05
100
Feedback
Search any
task
Search any
task