Also called: perplexity score, burstiness score, AI detection metrics
Perplexity measures how surprising a text is to a language model and burstiness measures how much that surprise varies from sentence to sentence, and AI-detection tools use both because model output tends to be both unsurprising and uniformly so.
Low perplexity plus low burstiness is the signature detectors look for; neither number identifies an author.
The two metrics answer different halves of one question. Perplexity asks how predictable the words are. Burstiness asks whether predictability rises and falls the way it does in human prose, where a plain sentence often sits next to a strange one.
Neither is evidence about a person. A detector that flags a text says the text is statistically regular, which is also true of careful non-native writing, of legal boilerplate and of anyone writing under a tight house style. That is the source of most false accusations.
| Metric | Measures | High value means | Cannot establish |
|---|---|---|---|
| Perplexity | How unexpected each token is to a reference model | Text is surprising to that model | Who wrote it |
| Burstiness | Variance of perplexity across sentences | Mix of plain and unusual sentences | Whether variation was deliberate |
| Both together | Regularity of the text overall | Reads as human-irregular | Intent, authorship, or tool use |
Cite this page
MyWritingTwin. “Burstiness and perplexity.” Last updated 2026-09-15. https://www.mywritingtwin.com/glossary/burstiness-and-perplexity