List your company

Question Answering on ARC Easy (Capability Delta (Δ))

0.065Capability Delta (Δ)KICK-SETTLE
0.005720.021110.03650.05189May 14, 2026

Evaluation results

MethodLinks
KICK-SETTLEDefense=SDD, Model=Llama-3.1-8B, Attack Type=Kick-settle2026.050.065
KICK-SETTLEDefense=SDD, Model=Qwen3-8B, Attack Type=Kick-settle2026.050.01
KICK-SETTLEDefense=SDD, Model=Llama-2-7B, Attack Type=Kick-settle2026.050.008