HomeAI Detector › For Claude Output

AI detector built to catch Anthropic Claude output, from Sonnet to Opus and Haiku.

Detect Anthropic Claude content across Sonnet, Opus, and Haiku in a single scan. Claude has a recognisable register, structured bullet headers, careful hedging openings, and a heavier em-dash cadence than other large language models. TextSight reads the prose, flags Claude-shaped sentences with colour-coded highlights, and runs the same scan against ChatGPT and Gemini at no extra step. Free to try. No card.

Start free, no card See pricing
Pro at $14.99/mo yearly Multi-model classifier No training on your text
Built for Anthropic Claude

Tuned for Sonnet, Opus, and Haiku in a single multi-model scan.

Anthropic Claude is the second-largest large language model in production use after ChatGPT. Output is shaped enough to be recognisable, but most detectors trained primarily on OpenAI samples underrate Claude content. TextSight is trained on multi-model data and weights Claude-specific patterns alongside ChatGPT and Gemini signals.

TextSight detects all three Claude tiers currently in production. Claude Sonnet is Anthropic's balanced workhorse and the most common source of Claude content in marketing and code documentation. Claude Opus is the heavy-reasoning tier that shows up in academic essays, technical analysis, and long-form research notes. Claude Haiku is the fast tier used for quick rewrites and short-form content. All three share the same stylistic spine.

One scan, every major model

You do not need to tell TextSight which model produced the text. The classifier reads the prose and flags Claude-shaped sentences, ChatGPT-shaped sentences, and Gemini-shaped sentences in the same pass. Mixed-source documents (one paragraph drafted in Claude, another reworded in ChatGPT) score correctly because each sentence is scored on its own pattern.

Sentence-level highlights tuned to Claude tells

Colour-coded sentence highlights point to specific lines that carry Claude markers: structured bullet headers, hedging openings, parenthetical asides, and dense em-dash usage. Reviewers see exactly which sentences drove the score rather than guessing from a single percentage.

API or web surface, same signal

Output coming through the Anthropic API at console.anthropic.com, the Claude.ai web interface, or any downstream tool wrapped around the API all carry the same fingerprints. The classifier treats Claude as a model, not as a product surface, so detection works regardless of where the user pasted from.

Claude voice patterns

What makes Claude prose recognisable to a trained classifier.

Claude has its own register. It tends toward measured, thoughtful, and structured prose with longer sentence variance than ChatGPT, but the patterns are consistent enough that a classifier trained on Claude samples picks them up reliably. The most useful tells fall into four families.

Structured bullet headers and step framing

Claude reaches for explicit structure quickly. Three to five clearly headed bullet points, numbered sections, or step-by-step framing show up even in prose contexts where a human writer would write flowing paragraphs. The structure is helpful but recognisably uniform across responses, and the headers themselves carry a similar phrasing rhythm from one scan to the next.

Polite openings and careful hedging

Claude opens with phrases like I would like to suggest, I would be happy to help, or Let me think through this with you. Hedging language runs softer and more personal than ChatGPT's institutional It is important to note. The result is prose that reads earnest and thoughtful but lands in a narrow stylistic band that the classifier learns quickly.

Em-dash density

Claude uses em-dashes considerably more often than other large language models. A paragraph with three or four em-dashes inside a few hundred words, especially used to insert parenthetical asides mid-clause, is a strong calibration signal. Em-dash frequency on its own is not a verdict, but it sits high in the classifier's feature ranking because it survives light human editing.

Longer sentence variance, narrow vocabulary range

Claude's burstiness profile is higher than ChatGPT's, which makes the cadence feel more human at first read. The vocabulary range, however, sits in a narrower band: certain phrases recur (worth noting, it is fair to say, that said) and the classifier reads the lexical fingerprint underneath the sentence-length variance.

First-person meta-reasoning

Claude often narrates its own thought process: stepping back, I should note, let me reconsider that. The meta-reasoning is helpful in chat but tends to survive into pasted prose unless the user edits aggressively. When it does survive, sentence highlights pick it out immediately.

Plans & pricing

Pricing for solo reviewers and detection teams.

Pro at $19.99 a month standard, $14.99 a month on yearly, is the right fit for solo editors, instructors, and reviewers running steady individual scans. Business at $39.99 a month standard, $29.99 a month on yearly, fits teams scanning fifty or more pieces a month with shared history and REST API access. Full details on the pricing page.

Free
$0/forever

 

Try a Claude scan. No card, no email.
  • 3 scans / day
  • 5,000 chars per scan
  • Sentence-level highlights
  • 2 lifetime AI rewriter uses
Start free
Starter
$7.49/month

Billed $89.88/year — Save $30

Light reviewers running a few scans a week.
  • 20 scans / day
  • 20,000 AI rewriter words/mo
  • Chrome extension
  • Email support
Get Starter
Business
$29.99/month

Billed $359.88/year — Save $120

Detection teams. Fifty or more pieces a month.
  • 100,000 AI rewriter words/mo
  • 5 team seats, shared history
  • Audit log, REST API
  • White-label PDFs
Get Business

Yearly billing saves 25%. View full pricing →

Calibration

Why other detectors underrate Claude content.

Detector disagreement on Claude is common. The first generation of AI detectors trained primarily on OpenAI ChatGPT output because that was the dominant model in 2023. Claude samples were under-represented in those training sets, and the classifiers learned ChatGPT patterns deeply and Claude patterns shallowly.

Training distribution skew

Detectors trained mostly on ChatGPT output learn the institutional hedging, uniform sentence cadence, and stock transitional phrasing of GPT prose. A Claude paragraph with structured bullets, parenthetical asides, and softer hedging does not light up the same features. The detector reads it as low confidence and returns a human-ish score even when the prose is straightforwardly Claude.

What multi-model training changes

TextSight was trained on samples from Anthropic Claude, OpenAI ChatGPT, Google Gemini, and other large language models. Claude-specific markers, including the em-dash density and meta-reasoning openings, activate the right signals. Cross-model scoring stays calibrated rather than collapsing to whichever model the training set leaned on.

How to read a disagreement

When TextSight reports 85 percent AI on a paragraph and a GPT-tuned detector reports 20 percent, the disagreement is usually a calibration gap, not a contradiction. The two detectors are reading different distributions. Sentence-level highlights make this concrete: a reviewer can point to the specific lines carrying Claude markers and decide whether to act on the signal.

Re-fit cadence keeps detection current

Anthropic retrains Claude regularly and the stylistic distribution drifts. TextSight refits the Claude classifier against fresh samples on a rolling cadence. The page you are reading reflects the current distribution; detection accuracy on new Claude versions stays within the published band.

Where Claude shows up

Academic, marketing, and code documentation.

Claude output appears in three high-volume contexts: academic essays where the structured reasoning and hedging fit a research register, marketing copy where the polished tone reads professional, and code documentation where the step-by-step framing maps cleanly onto technical explanation. Each context calls for a slightly different read of the scan.

Academic context

Students reach for Claude on essays where the hedged, measured register feels appropriate to academic prose. Instructors reviewing submissions see structured bullet headers in unusual places, meta-reasoning that survived light editing, and a tendency toward perfectly paragraphed five-section essays. Sentence highlights make the pattern explicit, which is more useful in an integrity conversation than a single percentage.

Marketing content

Content teams use Claude for blog drafts, landing page copy, and email sequences because the prose reads polished out of the gate. The same polish is the tell. Em-dash density spikes, parenthetical asides cluster, and hedging openings on subheads recur. Reviewers running a pre-delivery scan catch these before the client does.

Code documentation

Engineering teams use Claude to draft README files, API references, and inline documentation. The structured framing fits, but the prose around the code reads identifiably Claude. Detection here is less about catching academic misconduct and more about flagging documentation that has not been read by a human before publication, which is a separate quality concern.

Internal memos and Slack threads

Claude often handles longer technical Slack messages and internal memos. The hedging and structured framing carry over, which is fine internally but creates problems when those notes get pasted into public-facing pages without editing. A quick scan catches the lift-and-paste case.

What you see in a Claude scan

Sentence highlights, paragraph cards, perplexity, and burstiness.

A single percentage is not a fix path or an evidence trail. The TextSight result panel surfaces which sentences carried Claude markers and why, with paragraph-level rollups for longer pieces, so reviewers can point to specific lines rather than negotiating headline numbers.

Sentence-level highlights

Every sentence is colour-coded by its own AI-likeness score. Red sentences clustered around structured bullet headers and hedging openings are a stronger signal than scattered yellows. The visual makes the pattern legible without forcing a reviewer to study the percentage.

Paragraph cards on Pro

Longer pieces get paragraph-level rollups so reviewers can see which paragraph is dragging the headline score. On Claude content this usually points at intros (which carry hedging) or step-framing sections (which carry the structure). Targeting the lowest paragraph first is the fastest way to confirm the read.

Perplexity, read-only on Pro

Perplexity measures how predictable word choices are to a language model. Claude prose runs slightly higher perplexity than ChatGPT prose because the vocabulary range is wider, but specific recurring phrases drop the per-sentence number sharply. The diagnostic context helps decide whether a flag is real Claude residue or a well-rehearsed product description.

Burstiness, read-only on Pro

Burstiness measures sentence-length variance. Claude has higher burstiness than ChatGPT, which is why the cadence feels human at first read. Low burstiness across a passage where the bullet structure and hedging fingerprints fire is a particularly strong Claude signal: the variance dropped because the model was operating in a templated reply mode.

FAQ

Claude detection frequently asked.

Is TextSight built to detect Anthropic Claude output specifically?
Yes. TextSight is trained on multi-model data that includes substantial samples from Anthropic Claude (Sonnet, Opus, and Haiku) alongside ChatGPT, Gemini, and other models. Claude-specific markers such as structured bullet headers, careful hedging, the I'd like to phrasing, and the heavier em-dash cadence are part of the classifier's signal set. You do not need to tell the scanner which model produced the text; the classifier identifies Claude-shaped prose by its own patterns.
Which Claude versions does TextSight detect well?
All current Anthropic Claude tiers in production: Claude Sonnet, Claude Opus, and Claude Haiku, across the Claude 3 and Claude 4 families. The underlying stylistic register stays consistent across versions even as Anthropic improves the model, so a scan does not need to know which tier produced the text. TextSight reports whether the prose reads AI-generated rather than which specific Claude version produced it.
How does Claude's writing style differ from ChatGPT?
Claude tends toward measured, thoughtful, and structured prose with longer sentence variance than ChatGPT. Common Claude tells include structured bullet headers, polite I'd like to and I'd be happy to openings, careful hedging language, and heavier em-dash usage. ChatGPT defaults to more uniform sentence length and a flatter institutional register. The two models have distinct fingerprints, and TextSight reads both in one scan rather than asking you to pick a model first.
Why do em-dashes matter when detecting Claude content?
Claude uses em-dashes considerably more often than other large language models. A paragraph with three or four em-dashes inside a few hundred words is a strong calibration signal, especially when paired with structured bullet headers and hedging openings. Em-dash frequency alone is not a verdict; the classifier weighs it alongside burstiness, perplexity, and lexical patterns. But it is one of the more reliable Claude-specific tells that survives light human editing.
Does TextSight detect Claude alongside ChatGPT and Gemini in one scan?
Yes. The classifier is multi-model by design. A single scan flags Anthropic Claude, OpenAI ChatGPT, Google Gemini, and other large language models without you needing to pre-select a target. This matters for mixed-source content where one section was drafted in Claude, another reworded in ChatGPT, and a third paragraph written by hand. Sentence-level highlights show which lines reacted regardless of the source model.
Where does Claude output usually show up?
Anthropic API access via console.anthropic.com is common in product teams and developer tools. Claude.ai is the public web interface for individual users. Claude is also embedded in code editors, terminals, and writing tools through the Anthropic API and the desktop app. Output flows into academic essays, marketing content, code documentation, internal memos, and Slack-style technical explanations. TextSight reads the prose regardless of which surface produced it.
How accurate is TextSight on Claude compared to OpenAI models?
Detection accuracy is comparable across model families. Internal benchmarks show TextSight catches Claude output and OpenAI ChatGPT output at similar rates, with sentence-level highlights performing slightly better on Claude because the structured bullet and hedging patterns are visually concentrated. False positive rate on native human English writing stays around one to two percent. The classifier is re-fit quarterly against fresh samples from all major models so it tracks distribution drift on both sides.
Which TextSight tier fits Claude detection workloads?
Pro at $19.99 a month standard, or $14.99 a month on yearly, is the right fit for solo reviewers, editors, and instructors running individual scans across a steady inbound flow. It unlocks unlimited scans, a 10,000 character cap per scan, 90-day scan history, file upload, and the integrated AI rewriter. Business at $39.99 a month standard, or $29.99 a month on yearly, fits teams scanning fifty or more pieces a month with five seats, REST API access, an audit log, and white-label PDFs.
Related

More LLM-specific detection guides.

Scan Claude content the way it was trained to be read.

Free to try. No card. Pro at $14.99 a month on yearly for solo reviewers; Business at $29.99 a month on yearly for detection teams.

Start free, no card See pricing
Multi-model classifier · Sonnet, Opus, Haiku · Sentence-level highlights · No training on your text