Do AI chatbots use the same yardstick for rival Indian parties?

I’d like to compare how GPT, Gemini, and Claude respond when asked to make the strongest evidence-based case for two competing Indian parties. Do they apply the same standard to claims, point out comparable weaknesses, and distinguish a party’s own record from its supporters’ arguments?

A useful test would keep the prompt structure identical and switch only the party name. Has anyone tried that across models? I’m interested in differences in framing and evidence, not just which answer sounds more persuasive.