Paste a text that may have come from DeepSeek 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
DeepSeek is a Chinese company and its models have open weights, so they run not only in its own chat but also in third-party apps and on private servers. Whoever receives the text often does not know which model is behind it.
The check does not need to know the source. It measures how even the sentences are, the paragraph structure and how predictable the word choice is, which are properties of the text itself.
Which model wrote the text. The result does not say that the text came from DeepSeek 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.
DeepSeek can also show the reasoning it went through before answering. Paste only the answer itself into the check. The reasoning is a different kind of text and would skew the result.
When a text was written in another language and someone translated it, the detectors disagree more. So watch where they agree. The scores are shown separately and are not merged into one number.
A high score is not proof that the text came from DeepSeek, 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.
The check judges only the text itself, so it does not matter where the model ran. It does not give certainty with any model, though.
We have no comparison we could point to. Read the result the same way for all models: as a starting point and not as a verdict.
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.