When you ask ChatGPT about a specific company, it gets at least one thing wrong in about half of its answers. We checked almost 50,000 answers from AI assistants about 116 B2B technology companies against verified facts, and ChatGPT made an error in 49% of its answers and a serious error in about one in 20. That made it the most accurate of the three assistants we could compare properly, since Perplexity got something wrong in 63% of its answers and Gemini in 83%.
This research answers a narrow question, and it helps to be clear about which one. We didn’t test ChatGPT on maths, coding or general knowledge. We asked the questions B2B buyers ask about the companies they are considering, then compared each answer with a pack of verified facts about that company, which shows how well ChatGPT describes a business to the people who might buy from it.
At a glance
- ChatGPT got something wrong in about half of its answers about companies, compared with 65% across all the assistants we checked.
- The most common mistake was confident detail that the company had never published, such as a figure or a certification.
- The average answer left out four or five verified facts, which is more than twice the number of errors it contained.
- About two thirds of errors had no source behind them, which means the assistant was working from memory.
- ChatGPT’s factual score slipped from 86 in April to 72 in September, although our fact packs also became stricter over that period.
How accurate is ChatGPT compared with Perplexity and Gemini?
We scored every answer out of 100 for factual accuracy and logged each wrong claim along with how serious it was, checking more than 15,000 answers from each of the three assistants.
| Assistant | Factual score | Answers with an error | Answers with a serious error |
|---|---|---|---|
| ChatGPT | 79 | 49% | 5% |
| Perplexity | 71 | 63% | 16% |
| Gemini | 62 | 83% | 27% |
Based on Resonance’s analysis of almost 50,000 answers about 116 B2B technology companies between April and September 2026. We also checked Claude, Copilot, Google’s AI Mode and Google’s AI Overviews, although the samples were too small for a fair comparison.
ChatGPT comes out best, although being wrong in half of its answers is still a lot when the answer is about your company. Most of its mistakes were small, and only about 1% of its answers were graded critical.
Across everything we checked, the assistants were kinder than they were accurate, with an average score of 82 for tone against 71 for factual accuracy. In practice your buyer gets a friendly description of your company that is often out of date on the detail.
What does ChatGPT get wrong about companies?
We sorted more than 80,000 errors from all the assistants by what they were about, and one pattern accounted for more than half of them. In 57% of errors the assistant had added specific details the company had never published, usually because a buyer had asked a precise question that no public page answered.
Two composite examples show what this looks like without naming anyone. One answer credited a compliance platform with halving a customer’s audit time, and another quoted a guaranteed service level on behalf of a hardware company, although neither company had published anything of the kind.
Product features and capability came up in about a third of errors, usually as integrations, deployment options or features that were described wrongly or made up. Compliance and certification appeared in about one error in ten, while pricing and licensing accounted for about 7% of errors, as did numbers and statistics.
Positioning errors ran in both directions. We saw a broad automation platform described as mainly an RPA tool, and a data provider presented as the market leader in Europe without any support in its fact pack. Errors about funding, company size, pricing or the people who run a company were less common, although they were more likely than others to be rated serious. Questions about a company’s press coverage and its executives produced the lowest factual scores of any question type.
What does ChatGPT leave out?
Omissions are harder to spot than errors because nothing on the screen looks wrong. The average answer missed four or five verified facts about the company, compared with fewer than two errors, and about a third of those gaps concerned the range of products and capabilities a company offers. Another fifth concerned security and compliance, mainly data residency and certification, which are often the first things buyers in regulated sectors look for.
A useful test is to ask ChatGPT what your company offers and compare the answer with your full product list, since a missing product rarely shows up in any other way.
Why does ChatGPT get things wrong?
From June we also recorded where each error most likely came from. Our judge only blamed a page when that page plainly supported the wrong claim, so these figures are deliberately cautious.
About two thirds of errors across all the assistants had nothing behind them, which suggests the model knew the company only vaguely and filled in the rest from memory, and for ChatGPT the figure was 61%. The company’s own pages were behind 18% of errors overall and 27% of ChatGPT’s, usually because the assistant stretched something the company had said. Third-party pages accounted for 9% of errors overall and 6% of ChatGPT’s, and the source of the remainder was unclear.
When a page is to blame, it is more often your own, although third-party errors tend to do more harm, with 15% of them rated serious compared with 7% of the errors that came from a company’s own pages. Changing what a model remembers takes longer than fixing your own site, because it depends on the rest of the web describing you consistently over many months.
If you want to know which pages the assistants lean on in the first place, we looked at that question in What AI reads before it recommends.
The full research, free
What AI gets wrong about B2B tech brands has the full charts, the themes behind the errors and a comparison of the assistants, along with a note on how we did the checking. It runs to 12 pages, and there’s no form to fill in.
Is ChatGPT getting more or less accurate?
ChatGPT’s factual score slipped from 86 in April to 72 in September. Over the same period Gemini dipped during the summer, while Perplexity ended the period higher than it started, at 77.
We would treat ChatGPT’s drop with some care, because our fact packs became more detailed over those months and that made the test harder to pass. Part of the fall reflects ChatGPT’s answers, and part of it reflects us checking more closely.
About one error in ten came back in later answers, and those repeat errors are the ones we would chase first.
How can you check what ChatGPT says about your company?
Start by asking ChatGPT the questions your buyers ask, including questions about you by name, about your category and about how you compare with competitors on price and compliance. Then put the same questions to the other major assistants, because they tend to get different things wrong.
For each answer, note the errors and gaps along with the sources it cites, then compare it with a short fact sheet of the things you would want any buyer to know. Repeat the exercise every month, because the answers change as the models and their sources change.
The process becomes slow once you have more than a handful of questions. Agentcy, the platform behind this research, asks the questions on a schedule and checks each answer against your facts, and if you’d like to see what it finds for your company, we’ll run a free AI accuracy snapshot.
How do you fix what ChatGPT gets wrong about your company?
Most errors fill a gap in what a company has published, so the work is to close those gaps in public. We would start with your own site because it is the quickest source to change.
- Publish the details buyers ask about. Put your pricing approach, certifications, integrations and data residency in plain text on a dated page, so the assistant has something precise to quote.
- Read your own pages the way an assistant would. Look for loose claims that could be stretched, old product names and figures that appear without context, and tighten them before they turn up in answers.
- Correct the third-party pages with the most reach. Update your profiles on review sites and directories, and ask publishers for a correction where an error keeps appearing.
- Get your story into the media the assistants read. For B2B technology that mostly means the trade press, and we identified the titles in Earned media in the age of AI answers.
- Check again every month and judge progress over a quarter, because answers drawn from memory change slowly.
Our B2B tech PR team does this work with clients, alongside the media relations that shape what the assistants read.
Questions people ask about ChatGPT's accuracy
Is ChatGPT accurate about companies?
ChatGPT is mostly right on tone and often wrong on detail. In our checks of B2B technology companies it got at least one thing wrong in about half of its answers and made a serious error in about one in 20, which still made it the most accurate of the three assistants we compared.
Does ChatGPT make things up about companies?
It sometimes does, and invented detail was the most common error we found. The assistant added a figure, feature, integration or certification the company had never published, most often when a buyer asked a precise question that the company’s public pages didn’t answer.
Where does ChatGPT get its information about companies?
ChatGPT draws on what it learned in training and, when it searches, on the pages it cites. In our data about two thirds of its errors had no supporting source, which means they came from memory, and when a page was behind an error it was more often the company’s own site than a third-party one.
Can you correct what ChatGPT says about your company?
You can’t edit its answers directly, although you can change what it reads. Publish the specifics on your own site in plain, dated text and fix any claims that could be stretched, then correct the review sites and directories it relies on. Answers drawn from memory change more slowly, so keep your story consistent and check again every month.
Which AI assistant is most accurate about B2B companies?
Of the three assistants we could compare fairly, ChatGPT was the most accurate, with a factual score of 79 out of 100 compared with 71 for Perplexity and 62 for Gemini.
Where to start
Ask the main assistants the five questions your buyers ask most often, and write down every mistake and every gap you find. Then fix the pages you control, and check what has changed a month later.
If you would rather we did it, ask for a free snapshot and we’ll send you what the assistants say about you, along with where their mistakes come from.
This post draws on What AI gets wrong about B2B tech brands (Resonance, 2026), which used Agentcy to check almost 50,000 answers from ChatGPT, Gemini, Perplexity and other assistants about 116 B2B technology companies against verified facts between April and September 2026. Error sources were recorded from June 2026.
