Study reveals significant political bias in xAI's Grok 4.7 and OpenAI's GPT-6.1 Sol

A Convovo study, led by Cornell professor Tapan Parikh, found that when forced to recommend a single candidate across nearly 500 midterm races, xAI's Grok 4.7 picked the Republican in 92% of responses, while OpenAI's GPT-6.1 Sol picked the Democrat in 97%. The models disagreed in over 90% of races. When search was disabled, GPT maintained its Democratic lean, but Grok's Republican preference vanished, with the model refusing to choose in most cases.