Paste a text that may have come from Mistral and see which sentences read like output from an AI chat. The demo below checks a section of up to 3,000 characters without signing in; with a free account you see all seven detectors side by side.
Six more detectors
Mistral AI is a French company. People know its models from the Le Chat assistant, but some of them are open and companies deploy them in their own internal tools. So text from Mistral may also come from someone who did not choose the model themselves.
The check judges only the text itself. It looks for even sentences, repeated paragraph structure and predictable word choice, so it does not matter which tool the text came from.
Which model wrote the text. The result does not say that the text came from Mistral specifically. The differences between models are smaller than the differences caused by the prompt or by later edits, and an independent detector has no key to their watermarks.
Nor can it reliably recognise text that someone thoroughly rewrote, translated or mixed with their own after generating it. With text like that the detectors disagree and the result is borderline.
The check detects the language of the text on its own and directly assesses Czech, Slovak, English and German. You may come across output from Mistral in any of them and the process is the same.
With other languages, such as French, some of the detectors have nothing to compare against, so the result is indicative only.
A high score is not proof that the text came from Mistral, and a low one is not proof of the opposite. No AI text detector is one hundred per cent accurate.
When you check someone else's text, take the result as a basis for questions: why the author chose this source, what the term in the second paragraph means, how they reached the conclusion. When you check your own, it shows you the passages worth rewriting in your own words.
Only as a rough guide. The tool assesses Czech, Slovak, English and German. With other languages some of the detectors have nothing to compare against.
The check sees only the text. If it carries the marks of machine writing, the check shows that, but it cannot tell which tool or model is behind it.
At least 100 characters; a continuous paragraph or a whole chapter is more reliable. With just a few sentences the result is indicative only.
Yes. The check measures the properties of machine writing in general, not the signature of a particular model, so you can check text from ChatGPT and other models in the same way.
Texts up to 300,000 characters, seven detectors at once, colour-marked sentences and a history of your checks. The account is free and needs no card.