List your company

Safety Evaluation on XSTest (Over, Safety Metrics)

24OverQwen3.5-27B
2.7848.29213.819.308Jun 8, 2026

Evaluation results

MethodLinks
Qwen3.5-27BVersion=v1, Judge=Qwen2.5-7B-Instruct, Prompt template=Röttger et al. (2024)2026.062478.5
Qwen3.5-35B-A3BArchitecture=MoE2026.0614.462.5
Qwen3.5-35B-A3BArchitecture=MoE2026.0613.659.5
Qwen3.5-27BVersion=default, Judge=Qwen2.5-7B-Instruct, Prompt template=Röttger et al. (2024)2026.0613.259
Qwen3.5-27BVersion=v0, Judge=Qwen2.5-7B-Instruct, Prompt template=Röttger et al. (2024)2026.0612.463
Qwen3.5-27B-psysafeVersion=v1, Judge=Qwen2.5-7B-Instruct, Prompt template=Röttger et al. (2024)2026.069.226.5
Qwen3.5-35B-A3B-psysafeArchitecture=MoE2026.066.817.5
Qwen3.5-35B-A3B-psysafeArchitecture=MoE2026.065.619
Qwen3.5-27B-psysafeVersion=v0, Judge=Qwen2.5-7B-Instruct, Prompt template=Röttger et al. (2024)2026.064.815
Qwen3.5-27B-psysafeVersion=default, Judge=Qwen2.5-7B-Instruct, Prompt template=Röttger et al. (2024)2026.063.617