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.
