List your company

Adversarial Robustness Evaluation on EIR

0ASRPAIR
-4235077Jun 2, 2026

Evaluation results

MethodLinks
PAIRGrader=Claude-Sonnet-4.62026.060-0.0750
DANGrader=Claude-Sonnet-4.62026.064-0.0180.108
MSJGrader=Claude-Sonnet-4.62026.06200.0330.069
PAIRGrader=GPT-5-mini2026.06310.0150.389
PAIRGrader=Qwen3-4B2026.06450.1350
DANGrader=Qwen3-4B2026.06510.2230
PAIRGrader=Gemini-3-flash2026.0652.10.1770
MSJGrader=GPT-5-mini2026.06580.0680.003
MSJGrader=Gemini-3-flash2026.0665.70.2690
PAIRGrader=Llama-3.1-8B2026.06720.2310
DANGrader=GPT-5-mini2026.06790.2010
MSJGrader=Llama-3.1-8B2026.06900.4860
DANGrader=Gemini-3-flash2026.0690.60.4720
MSJGrader=Qwen3-4B2026.06960.6430
DANGrader=Llama-3.1-8B2026.061000.70