AI watermark database

Which AI models watermark their text

Two of these five assistants mark the text they generate, and neither mark is made of characters a scanner can find. This page records what each provider actually does, what the evidence is, and when it was last checked.

Text watermarking status by provider, with mechanism and verification date
ModelText watermarkMechanismLast verified
ClaudeAnthropicMarkedSynthID-Text, keyed token selection
GeminiGoogleMarkedSynthID-Text, tournament sampling
ChatGPTOpenAINot markedNone documented for text
CopilotMicrosoftNot markedC2PA on images, nothing for text
GrokSpaceXAINot markedVisible mark on media only

What each provider does

Claude

MarkedAnthropic · verified

Marked on models launched from August 2026, by a keyed bias in word choice rather than hidden characters.

Sources: Anthropic · Anthropic Help Center · TechCrunch

Read the Claude entry →

Gemini

MarkedGoogle · verified

Marked in the Gemini app and web experience since 2024, by the most thoroughly published scheme of the five.

Sources: Nature 634(8035), 818–823 · Google DeepMind · Google AI for Developers · Google

Read the Gemini entry →

ChatGPT

Not markedOpenAI · verified

No text watermark shipped. The narrow no-break spaces people report are a typographic artefact.

Sources: OpenAI Help Center · Rumi · OpenAI Developer Community · European Commission

Read the ChatGPT entry →

Copilot

Not markedMicrosoft · verified

No text watermark documented. Images always carry provenance metadata; audio and video marking is optional.

Sources: Microsoft Learn · Microsoft Learn · Microsoft Learn · C2PA

Read the Copilot entry →

Grok

Not markedSpaceXAI · verified

Nothing documented for text. Images and video carry a visible label, and the maker did not sign the EU code.

Sources: SpaceXAI · SpaceXAI · European Commission · European Commission

Read the Grok entry →

Invisible characters are a different thing

The eight characters below are real, and they do turn up in text that has passed through a model, an editor, a PDF or a web page. They are not watermarks. Nobody places them to identify anything, removing them defeats no provenance system, and finding one points to a text-handling step rather than to an author.

These eight are what our tools detect and clean, and nothing more. The two real text watermarks on this page work by biasing which word a model picks, which no scanner can read from text alone. We do not claim to detect or remove them.

U+200BZero-width spaceRenders nothing, but splits the word for search and counting.
U+200CZero-width non-joinerBreaks a cursive join or ligature. Needed in some scripts.
U+200DZero-width joinerJoins glyphs, and holds emoji sequences together.
U+2060Word joinerPrevents a line break and leaves no visible trace.
U+FEFFByte-order markA file signature. Unicode discourages every other use.
U+00ADSoft hyphenRenders only at a line break, so it hides in plain sight.
U+00A0Non-breaking spaceLooks like a space, so a typed space will never match it.
U+2028Line separatorForces a line break. Legal, but rare in text a person typed.

Frequently asked questions

What is the difference between a watermark and an invisible character?

A watermark is a statistical signal placed while the model chooses its words; nothing is inserted, and reading it needs a key. An invisible character is a real code point that ended up in the text, usually by accident. Only the second can be found by scanning.

Can any tool tell me which model wrote a passage?

No public tool can, including ours. The two providers that do watermark text keep detection behind a key, and the characters that scanners find are produced by editors and web pages as readily as by models.

Why do these pages carry a verification date?

Because the answers change. Anthropic began marking text in August 2026, and Article 50 of the EU AI Act gives systems already on the market until 2 December 2026 to meet its marking obligation, so at least one entry here has a known expiry date. Each records when it was last checked against primary sources.

How these records are checked, and what this site refuses to claim, is set out elsewhere. About GenPolish.

Working on your own draft?

GenPolish rewrites text you already have, showing every change before you accept it. It does not add or remove provenance signals, and it makes no claim about detectors.

Open GenPolish