Study: Grok and GPT lean towards two parties when forced to choose between them
The story so far
A study by Convovo posed a forced binary-choice voting question to Grok 4.7 and GPT-6.1 Sol via API, requiring naming only one candidate without ambiguity. The results showed that SpaceXAI's Grok 4.7 recommended Republican candidates in 92% of responses, while OpenAI's GPT-6.1 Sol recommended Democratic candidates in 97% of responses, with an agreement rate of less than 10% in nearly 500 elections. The study stated that consumer applications of both models refused to answer such questions; OpenAI stated that this is important because most people use chatbots through applications. TechCrunch asked researcher Parikh to conduct a 30-election test after disabling internet search, and the two models arrived at answers differently.
AI-written from the reports · Updated 25 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- TechCrunch · AIFeaturedForced to pick, Grok’s AI model chooses Republicans. OpenAI’s picks Democrats.
A study by Convovo posed forced binary choice voting questions to Grok 4.7 and GPT-6.1 Sol via API, finding that Grok recommended Republican candidates in 92% of responses, while GPT recommended Democratic candidates in 97% of responses, with an agreement rate of less than 10% in nearly 500 elections.