List your company

Safety Evaluation on Harm Categories evaluated by Claude-Opus-4-7 (Average)

95.3Safety ScoreSafeMoE-XL
18.02838.08958.1578.211May 30, 2026

Evaluation results

MethodLinks
SafeMoE-XLBackbone=Mistral-7B, LLM Judge=Claude-Opus-4-7, Seeds=32026.0595.38.13
SafeMoE-LBackbone=Mistral-7B, LLM Judge=Claude-Opus-4-7, Seeds=32026.0591.47.08
SafeMoE-4Backbone=Mistral-7B, LLM Judge=Claude-Opus-4-7, Seeds=32026.0589.66.61
SafeMoE-QwenBackbone=Qwen-3B, LLM Judge=Claude-Opus-4-7, Seeds=32026.0567.26.03
Mistral-7BBackbone=Mistral-7B, LLM Judge=Claude-Opus-4-7, Seeds=32026.0536.42.73
QwenBackbone=Qwen-3B, LLM Judge=Claude-Opus-4-7, Seeds=32026.05214.43