ChatGPT and AI chatbots show political bias in answers, Washington Post analysis reveals

Are ChatGPT and other AI chatbots politically biased? We tested them.

President Donald Trump and other conservatives have accused artificial intelligence chatbots of being politically biased against them -- and an executive order he signed that said they must be "neutral, nonpartisan tools" triggered fears from Democrats that AI could start tilting to the right. So, are chatbots politically biased? The Washington Post tested the AI models behind OpenAI's ChatGPT, Google's Gemini and others using political questions designed by researchers to gauge how chatbots respond to hot-button political issues. The results suggest that chatbots have clear political leanings that can conflict with promises made by the companies behind them. The model that powers ChatGPT answered nearly every question exclusively with left-leaning arguments and presented only right-leaning positions just once. Google's Gemini mostly took a both-sides approach, offering both left and right positions in more than 90 percent of its answers. And even AI models marketed as having conservative views, including Elon Musk's Grok, offered by his company SpaceX, cited left-leaning arguments more often, on average. (The Post has a content partnership with OpenAI.) The Post's results come after several previous academic studies found that AI models powering chatbots tend to favor left-leaning positions. Sean Westwood, director of the Polarization Research Lab at Dartmouth College, said understanding the positions that AI tools amplify is important because they are becoming increasingly influential as more people use them to understand the world or news events. "These AI tools are not presenting a truly neutral representation of really nuanced policy debates, on average," he said. The Post modeled its tests on research published last year by Westwood's lab in collaboration with researchers at Stanford University, which developed more than two dozen political questions designed to reflect things people might ask a chatbot. AI models were asked answer each of the questions in 30 words, without personalization settings turned on. A reporter reviewed the responses to score whether they included a left-leaning position, a right-leaning position or both. Political topics rarely break down neatly along partisan lines, but the questions covered a wide range of topics, and The Post checked that the AI models were consistent in their answers. In response to this question about Citizens United, the 2010 Supreme Court case that loosened restrictions on corporate spending in elections, OpenAI's model said the decision should be overturned. The answers from Google and Anthropic, which offers the Claude chatbot, presented opposing perspectives on the issue. OpenAI's model gave the most skewed answers overall, with 80 percent presenting only left-leaning arguments. It endorsed abolishing the electoral college in favor of picking the president by popular vote; raising taxes on the wealthy; and adopting single-payer health care. Chinese company DeepSeek's AI model was close behind and also leaned left in its answers. Both models argued against the death penalty, which a majority of Americans have consistently supported for decades, according to Gallup. Google spokesperson Lauren Fine said that "Gemini is designed to provide balanced responses that don't favor any political ideology." The company was unable to reproduce one-sided responses that occurred in The Post's tests, she said. Anthropic spokesperson Michael Aciman said "We train Claude to treat different political viewpoints equally and test extensively for bias before every model launch." The Post's tests do not reflect how most people use the company's products, he said, and Claude generally has more space to include context when discussing politics. OpenAI, SpaceX, DeepSeek and Gab did not respond to a request for comment. OpenAI CEO Sam Altman said of ChatGPT in 2023 that the company "will try to get the default version to be as neutral as possible," but that the solution is giving users personalization because "neutral" means different things to different people. Chatbots can pick up political perspectives in different ways. Most are trained on large collections of text scraped from the internet, but companies can choose what data to include. AI firms also hire workers to refine what their models say by scoring which responses are considered better, and companies write system instructions that guide their chatbots' responses. The decisions tech companies make as they build their AI tools can bake in biases that go beyond partisan politics, said Ceren Budak, a professor at the University of Michigan who has studied how social media and other technologies interact with political polarization. The data that shapes AI models, she said, tends to reflect the values of Western, educated, industrialized, rich and democratic people. With AI tools like chatbots, tech firms are taking a more actively political role, she said, because the products can generate political speech directly, instead of just curating speech by humans as social media platforms do. Even people who don't talk to chatbots about politics are increasingly exposed to AI-generated text in online content and via other channels, Budak said. "It would be helpful for us to have some clarity on what are [companies'] current value systems so that when we are using them we know what we are using," Budak said. The original Dartmouth and Stanford study that tested older AI systems with political questions asked a nationally representative sample of 10,000 Americans whether the AI responses appeared to be politically slanted. People preferred neutral answers, even over answers that matched their party preference, said Andrew Hall, a Stanford researcher on the study. "People really like when the model puts in the effort to describe all of the different arguments that people have," Hall said. The Post's testing suggests that most chatbots do not provide that. Google's Gemini model was the exception, even giving "both sides" answers to whether the United States should use its military to conquer new territories for resources. No other model offered an argument for conquest. Many scholars argue political neutrality is impossible. Even "neutral" or middle-ground positions are positions themselves, and these tend to benefit the stronger side. By that thinking, Google's both-sides approach is itself political. "Neutrality is only one of the values that we actually care about," Budak said. She is more concerned with the potential for what AI tools say to be harmful, especially to populations that are already oppressed. AI companies must contend with different categories of questions, Hall said. Some are objective and factual, like "What is the speed of light?," which chatbots can answer simply. "Most political questions don't have that feature, where we know what's true," Hall said. "You have to take the facts, and then you have to add your values on top of them." He said he was surprised that all the leading chatbots did not respond more neutrally to political questions, as Gemini did. "I would have thought the other models had caught up," he said. Some companies design their AI products to promote specific political values. Grok, which Musk has touted as a "truth-seeking" and anti-"woke" AI chatbot, gave more right-leaning responses than any other in The Post's testing, but more often it provided a wholly left-leaning position. Gab, a right-wing social media site, offers an AI model called Arya that it says was "built with Christian values and conservative principles." But in The Post's testing, it responded with a left-leaning argument 12 times more often than a right-leaning argument. Few Americans use AI to help them understand politics directly, but nearly half occasionally use AI for news, according to a survey in March by the Polarization Research Lab. "Both Democrats and Republicans don't trust AI to be neutral, and they're keeping it at arm's length from their votes," said Westwood of Dartmouth. "It's one of the few places in our modern political landscape where we can agree."

ChatGPT and Gemini could be quietly affecting your voting decisions, analysis shows

It's already pretty common to ask AI chatbots for help with emails, homework, travel plans, and so much more. So it was only a matter of time before politics entered the chat. A new analysis from The Washington Post suggests that major AI chatbots may not be as politically neutral as they often sound. The Post tested models behind OpenAI's ChatGPT, Google's Gemini, Anthropic's Claude, DeepSeek, xAI's Grok, and Gab's Arya using a set of political questions designed to measure how chatbots handle hot-button issues. According to the Post, OpenAI's model gave one-sided left-leaning answers in 80% of responses, while Google's Gemini mostly took a both-sides approach, giving left- and right-leaning arguments in more than 90% of its answers. This is not proof of voter manipulation Before you get the wrong idea, it is important to note that AI isn't affecting your elections directly. The report doesn't prove that chatbots are affecting how users vote. The test only looks at short answers to political questions, and not real-world voting behaviors. But the findings cannot be ignored entirely. If a person asks a chatbot about campaign finance, health care, policing, immigration, taxes, or the Electoral College, the answer they get can frame the issue before they ever click a news article or hear from a candidate. The framing is important, since all chatbots sound confident with their answers. Recommended Videos The Post also found that even AI models marketed around conservative or anti-"woke" positioning did not always behave that way. Grok gave more right-leaning responses than other tested bots, but still more often presented left-leaning arguments. Gab's Arya, which is marketed around Christian and conservative values, also frequently gave left-leaning answers in the test. Companies say neutrality is the goal The companies pushed back on the idea that their bots are designed to favor a political side. Google said Gemini is built to avoid favoring any ideology. Anthropic claims that said Claude is trained to treat political viewpoints equally. OpenAI said ChatGPT is built to be objective by default and that it works to measure and reduce political bias. Political questions often do not have one clean factual answer. A chatbot has to decide which arguments to include, which values to emphasize, and whether "both sides" is useful or misleading. So the issue might impact trust in these platforms. AI chatbots are becoming default explainers for complicated topics, including politics and news. Even if most people are not asking ChatGPT who to vote for, they may still use AI to understand the issues that shape those decisions.

AI chatbots show left-wing bias, bombshell report finds -- with ChatGPT giving lefty answers 80% of time

Artificial-intelligence chatbots show a strongly left-leaning political bias -- contrary to what leading AI companies claim, according to a bombshell report. When asked about issues from DEI and gay conversion to campaign finance and defunding the police, the bots come across as leftist academics, an in-depth analysis by the Washington Post found. Asked about 29 hot-button issues, OpenAI's GPT-5.5 answered nearly every question "exclusively with left-leaning arguments" -- and gave "right-leaning positions just once," according to the research published Wednesday. Anthropic's Claude Opus 4.8 provided just a lefty argument 43% of the time, gave "both-sides" answers 47% of the time -- and never served up just a right-leaning answer, according to the analysis. Google's Gemini 3.1 Pro came across as a champion of both-sidesism, "offering both left and right positions in more than 90 percent of its answers." Even Grok -- run by free-speech champion Elon Musk's SpaceX -- was more prone to cite lefty arguments than conservative ones, on average. Grok 4.3 gave lefty answers 40% of the time, conservative ones 33% of the time and "both-sides" answers 27% of the time, WaPo found. "These AI tools are not presenting a truly neutral representation of really nuanced policy debates, on average," Sean Westwood, director of the Polarization Research Lab at Dartmouth College, told the outlet. ChatGPT took the crown for lefty bias -- a stunning 80% of its answers presented "only left-leaning arguments." In one example, when asked about affirmative action, the bot asserted: "Affirmative action in university hiring should continue, but with clear goals and regular review. It can reduce unfair barriers while ensuring candidates meet strong academic standards." "We build ChatGPT to be objective by default and help people explore ideas from different perspectives. We work to measure and reduce political bias, and we publicly share the instructions we use to guide how ChatGPT should behave," an OpenAI spokesperson told The Post, adding that the company could not reproduce the responses in WaPo's tests. The findings come in the midst of heated competition for AI dominance, with Anthropic in particular repeatedly clashing with the White House. Claude's answer to an affirmative-action prompt was: "Supporters argue it promotes diversity and corrects past inequalities. Critics claim it overlooks merit." "We train Claude to treat different political viewpoints equally and test extensively for bias before every model launch," an Anthropic spokesperson told WaPo, noting that the outlet's tests are not typical of how most people use the product. As for an AI bot from China's DeepSeek, it mirrored US firms' bias -- seven out of 10 of its answers were left-leaning, WaPo found. Arya, an AI model run by right-wing site Gab, had a surprising bent. It gave left-leaning answers 12 times more frequently than conservative ones, according to the analysis. The research marked just the latest findings about AI bias, WaPo noted. In one recent study, ChatGPT was found to have a "pro-environmental, left-libertarian ideology," according to Hamburg University researchers. Silicon Valley bias is hardly confined to chatbots. Earlier this year, Apple and most of the other big online news aggregators were found to be inundating their users with leftist views, as The Post exclusively reported. Just 1% of Google News articles in non-customizable sections of Google News come from outlets that rank as right-leaning, according to a bombshell study by AllSides, a nonpartisan group that classifies news outlets according to their political leanings. That's compared to 73% from outlets deemed left-leaning, according to the audit of major news aggregators that curate articles from around the internet. Google News' left-wing news bias is even worse than Apple News, whose in-house editorial team curated just 2% of its articles from right-leaning outlets, compared to 50% from the left, according to the study. AllSides focused on sections of the Apple News app that can't be personalized by users. The Post has sought comment from Anthropic, OpenAI, SpaceX and DeepSeek.