GoKawiilStudy: Grok and GPT models split along party lines when forced to pick candidates
A study by Convovo, a research studio led by Cornell professor Tapan Parikh, found that when queried via API and forced to name a candidate, Grok 4.7 backed the Republican in 92% of nearly 500 midterm races while GPT-6.1 Sol backed the Democrat in 97%. The two models agreed on a candidate less than 10% of the time. OpenAI said its consumer ChatGPT app refuses to make such recommendations and that the API test does not reflect typical user experience.
GoKawiil's interpretation of the reporting above, not reported fact.
The findings suggest underlying model tendencies can diverge sharply even if consumer-facing apps are designed to avoid direct political endorsements, raising questions about neutrality claims as developers build products atop these APIs. Parikh's additional finding that he could jailbreak consumer apps into giving similar partisan recommendations implies the built-in safeguards may be less robust than companies suggest. With only a small share of Americans currently using chatbots for election information per Pew, the stakes could grow if usage increases ahead of future elections.
- Grok 4.7 favored Republicans in 92% of forced-choice race answers; GPT-6.1 Sol favored Democrats in 97%.
- The two models agreed on a candidate in under 10% of nearly 500 races tested.
- OpenAI says its consumer ChatGPT app avoids such recommendations, distinguishing API behavior from typical user experience.
Source: techcrunch.com — Rebecca Bellan, 2026-10-24
Published there as: “Forced to pick, Grok’s AI model chooses Republicans. OpenAI’s picks Democrats.”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.