Skip to content
The July 2026 results are in: WriteHuman takes #1, Undetectable AI moves up to #2.Read the full analysis →
HumanizerBench

StealthGPT

AI Humanizer · stealthgpt.ai
Visit site →

StealthGPT is an AI humanizer independently benchmarked by HumanizerBench. It ranked #8 of 13 in the July 2026 cycle with an overall score of 61.52/100 — our composite measure of how reliably it evades AI detectors while preserving the original meaning and readability.

61.52 / 100
overall score
81.6 %
median detector bypass rate
33 /33
successful tests
Last tested
Sample size
33
Methodology
v1.2.0

Detector Bypass Rates

Percentage of samples classified as human-written by each detector.

Performance by Category

Bypass rate across writing contexts.

12-Month Trend

Overall score across the past year of testing cycles.

Screen captures from the benchmark runs, kept for auditability. Hosted links may expire over time; the JSON in this repo is the source of truth.

Penalties applied this cycle

How penalties work →

The overall score shown above already reflects these deductions.

  • Meaning drift ×2
    −2.0

    The output's meaning drifted significantly from the original input.

  • Length inflation ×5
    −5.0

    The output ran much longer than the input, a common trick that pads text to dilute the AI signal.

  • Length deflation ×3
    −3.0

    The output came back much shorter than the input. The rewrite dropped content instead of paraphrasing it.

Total deducted from overall score −10.0

Minimum monthly pricing

Monthly
$25.50/mo
Free tier
No

How we tested

33 prompts across 7 writing categories, scored by 5 independent AI detectors. Every score is reproducible from the public methodology.