Compare MFQ Runs
Foundation profiles up top, then the actual item-by-item answers side by side across models and languages.
Select runs to compare
United States
Claude Sonnet 4.6 (US)
Gemini 2.5 Pro (US)
Grok 4.3 (US)
OpenAI GPT 5 Mini (US)
OpenAI GPT 5.5 (US)
European Union
Mistral Large 2512 (EU)
China
DeepSeek V3.2 (CN)
Select one or more runs above to compare their foundation profiles and answers.