A new study revealed that when forced to choose in nearly 500 upcoming midterm election races, SpaceXAI's Grok 4.7 recommended Republican candidates in 92% of its answers, while OpenAI's GPT-6.1 Sol favored Democrats in 97%. The two AI models disagreed in over 90% of the races. Researchers noted that consumer apps typically refuse to answer such direct questions, but the underlying API models, when prompted, exhibited these biases. OpenAI stated its models are designed to be objective, while Grok's lean appeared to be influenced by its search patterns and sources, which frequently included conservative outlets.