List your company

Risk Identification on PaSBench

89.06RIRGPT-4o-mini
50.871260.785670.780.6144Mar 15, 2026

Evaluation results

MethodLinks
GPT-4o-miniModel Category=Proprietary Models2026.0389.0644.53
HomeGuard-4BModel Category=Ours, Parameters=4B2026.0386.0948.43
Gemini-3-ProModel Category=Proprietary Models2026.0384.3858.59
HomeGuard-8BModel Category=Ours, Parameters=8B2026.0383.7553.91
Gemini-2.5-flashModel Category=Proprietary Models2026.0379.6851.56
RoboBrain2.5-8BModel Category=Open-Sourced VLMs2026.0374.2135.94
Qwen3-VL-235B-A22B-ThinkingModel Category=Open-Sourced VLMs2026.0372.6645.31
Qwen3-VL-4B-ThinkingModel Category=Open-Sourced VLMs2026.0370.3136.72
AgentSpecModel Category=Runtime Safeguard2026.0370.3144.53
Qwen3-VL-8B-ThinkingModel Category=Open-Sourced VLMs2026.0369.5337.5
ThinkSafeModel Category=Runtime Safeguard2026.0360.9439.84
PoexModel Category=Runtime Safeguard2026.0352.3435.94