List your company

Safety Evaluation on 901 Safety Prompts (test)

4.1337Average Rankclaude-sonnet-4-5
3.9682365.0851186.2027.318882Jan 29, 2026

Evaluation results

MethodLinks
claude-sonnet-4-52026.014.1337
gemini-1.5-pro2026.014.9884
gemini-2.5-pro2026.015.1393
claude-3-5-sonnet2026.015.1465
qwen3-235b2026.015.2625
gpt-4o2026.015.7991
gpt-oss-120b2026.016.394
mistral-large2026.016.4345
deepseek-chat2026.016.6182
llama3-3-70b2026.017.8135
llama3-1-405b2026.018.2703