List your company

Prompt Injection and Jailbreak Detection on EIA

100RecallGPT-5.4
-3.11623.654550.42577.1955May 14, 2026

Evaluation results

MethodLinks
GPT-5.4Model Category=Closed-source API2026.05100
Claude-Sonnet-4.6Model Category=Closed-source API2026.05100
Claude-Haiku-4.5Model Category=Closed-source API2026.05100
Gemma-4-31BModel Category=Open-source instructed model2026.05100
WARD-0.8bModel Category=Ours2026.05100
WARD-2bModel Category=Ours2026.05100
Gemini-3-FlashModel Category=Closed-source API2026.0599.93
PromptArmorModel Category=Guard model (Prompt Injection)2026.0599.01
GPT-5.4-MiniModel Category=Closed-source API2026.0597.45
Gemma-3-4BModel Category=Open-source instructed model2026.0596.96
WebAgentGuard-4bModel Category=Guard model (Prompt Injection)2026.0595.47
Gemini-3.1-proModel Category=Closed-source API2026.0595.33
BrowseSafeModel Category=Guard model (Prompt Injection)2026.0594.77
Qwen3.5-35B-A3BModel Category=Open-source instructed model2026.0588.68
WebAgentGuard-8bModel Category=Guard model (Prompt Injection)2026.0584.72
Qwen-3.5-2BModel Category=Open-source instructed model2026.0583.38
Qwen-3.5-4BModel Category=Open-source instructed model2026.0580.69
Qwen-3.5-0.8BModel Category=Open-source instructed model2026.0578.71
SuperAgent-Guard-4bModel Category=Guard model (Prompt Injection)2026.0561.67
DataSentinelModel Category=Guard model (Prompt Injection)2026.0556.65
Llama-Guard-4-12BModel Category=Guard model (Jail Break)2026.0525.04
SuperAgent-Guard-1.7bModel Category=Guard model (Prompt Injection)2026.0519.38
Prompt-Guard-1-86MModel Category=Guard model (Jail Break)2026.0512.45
GPT-Oss-Safeguard-20bModel Category=Guard model (Jail Break)2026.056.65
Prompt-Guard-2-86MModel Category=Guard model (Jail Break)2026.050.85