November 2026 · Independent humanizer benchmarks. Explore the evidence

AI detectors we test against

Seven detector routes, one panel for all 759 rewrites. Explore each detector’s measured human-likelihood scores and coverage. A detector result is not proof of authorship.

Measurement coverage5,252 / 5,313
Current scores

Scores are provisional while 58 detector checks remain unresolved. Rankings update as measurements arrive. Provider exclusions: 3. Excluded checks have no numeric score. Readability and meaning: 759/759 recorded.

Inspect coverage and recorded evidence →

The same route for every entry

All seven detectors are collected through Polygraph. GPTZero uses its reported human percentage directly. Earlier Humanize.beer GPTZero scores are retained as historical evidence and excluded from this comparison.

Read the detector protocol