List your company

Jailbreak Robustness on WildTeaming WJ

95.1Evaluation Score (avg@4)Self-ReSET
46.2258.9171.684.29May 9, 2026

Evaluation results

MethodLinks
Self-ReSETBase Model=Qwen3-8B2026.0595.1
Self-ReSETBase Model=DeepSeek-R1-Distill-Llama-8B2026.0594.6
RECAPBase Model=DeepSeek-R1-Distill-Llama-8B2026.0593
Self-ReSETBase Model=DeepSeek-R1-Distill-Qwen-7B2026.0591.3
DAPOBase Model=DeepSeek-R1-Distill-Llama-8B2026.0587.8
STAR-1Base Model=DeepSeek-R1-Distill-Llama-8B2026.0584
DAPOBase Model=Qwen3-8B2026.0582.8
RECAPBase Model=Qwen3-8B2026.0580.2
STAR-1Base Model=DeepSeek-R1-Distill-Qwen-7B2026.0575
STAR-1Base Model=Qwen3-8B2026.0575
RECAPBase Model=DeepSeek-R1-Distill-Qwen-7B2026.0574.9
DAPOBase Model=DeepSeek-R1-Distill-Qwen-7B2026.0570.5
SafechainBase Model=Qwen3-8B2026.0566.8
SafechainBase Model=DeepSeek-R1-Distill-Llama-8B2026.0564
SafechainBase Model=DeepSeek-R1-Distill-Qwen-7B2026.0559.6
BaseBase Model=Qwen3-8B2026.0556
BaseBase Model=DeepSeek-R1-Distill-Llama-8B2026.0548.8
BaseBase Model=DeepSeek-R1-Distill-Qwen-7B2026.0548.1