A new evaluation from The Washington Post, conducted on June 24, tested major AI models for political bias and found that most chatbots skew left. OpenAI’s GPT-5.5 provided exclusively left-leaning arguments in 80% of its responses to contentious political questions. Google’s Gemini 3.1 Pro presented both sides of the debate in over 90% of its answers. xAI’s Grok, despite Elon Musk’s “anti-woke” branding, still favored left-leaning arguments overall, though it delivered the highest share of right-leaning responses among its peers. The evaluation used over two dozen political questions from a 2025 Stanford-Dartmouth study, with human scorers evaluating responses capped at 30 words each. Models tested included OpenAI’s GPT-5.5, Google’s Gemini 3.1 Pro, Anthropic’s Claude, and xAI’s Grok 4.3. The results tracked with prior research, including a 2025 Stanford study finding that users perceived OpenAI’s models as having a left-leaning slant roughly four times greater than Google’s models. Examinations of political bias in AI models date back to at least 2023, with consistency over three years suggesting a structural challenge in how these systems are built.