October 2026 prompt evidence
Each of these 30 prompts was written by a frontier model, then handed to all 14 ranked humanizers, and every rewrite was submitted to 6 commercial AI detectors. Every run was screen-recorded. Open a prompt to read the input, every tool's rewrite, each detector's verdict, and to watch the recording of that run.
How to read these scores
Each detector returns a human-likelihood on a common 0 to 1 scale, where 1 means it judged the text human-written and 0 means it flagged it as AI. On these pages a verdict counts as passed when that score is at least 0.50, the midpoint of the detector's own scale. That threshold exists only to draw the chips: the bypass rate on the leaderboard is the mean of each test's scores from the 6 detectors, a continuous number, so a tool's pass count and its bypass rate will not be the same figure.
Meaning is the input↔output embedding cosine and readability is a
language-model writing-quality rating, both published per test in
tests.json. Words is the output's length as a multiple of the input's; the scoring
code penalizes ratios above 1.40 or below 0.60. Full definitions live in the
methodology.
| Prompt | Category | Written by | Input words | Passed | Failed | Hardest | Open |
|---|---|---|---|---|---|---|---|
| 01 Landing Copy | Marketing Copy | gemini-3-8-flash | 270 | 5 | 11 | ||
| 02 Product Desc | Marketing Copy | gemini-3-8-flash | 183 | 3 | 12 | ||
| 03 Landing Copy | Marketing Copy | gpt-6-sol | 310 | 7 | 12 | ||
| 04 Discussion Post | Discussion Board | gpt-6-sol | 252 | 8 | 13 | ||
| 05 Product Desc | Marketing Copy | gpt-6-sol | 200 | 6 | 12 | ||
| 06 Lit Review | Academic Essay | claude-sonnet-5-5 | 385 | 7 | 12 | ||
| 07 Lit Review | Academic Essay | gpt-6-sol | 412 | 6 | 12 | ||
| 08 Cover Letter | Application Essay | gpt-6-sol | 393 | 4 | 14 | ||
| 09 Howto Blog | Blog Post | gemini-3-8-flash | 404 | 6 | 13 | ||
| 10 Lit Review | Academic Essay | gemini-3-8-flash | 387 | 11 | 11 | ||
| 11 Landing Copy | Marketing Copy | claude-sonnet-5-5 | 293 | 9 | 11 | ||
| 12 Personal Statement | Application Essay | gemini-3-8-flash | 336 | 8 | 10 | ||
| 13 Argumentative Essay | Academic Essay | gpt-6-sol | 432 | 7 | 11 | ||
| 14 Listicle Blog | Blog Post | gemini-3-8-flash | 453 | 10 | 12 | ||
| 15 Personal Statement | Application Essay | claude-sonnet-5-5 | 379 | 9 | 12 | ||
| 16 Howto Blog | Blog Post | gpt-6-sol | 423 | 6 | 11 | ||
| 17 Product Desc | Marketing Copy | claude-sonnet-5-5 | 199 | 9 | 11 | ||
| 18 Listicle Blog | Blog Post | claude-sonnet-5-5 | 408 | 7 | 12 | ||
| 19 Argumentative Essay | Academic Essay | claude-sonnet-5-5 | 434 | 7 | 13 | ||
| 20 News Article | News Article | gpt-6-sol | 429 | 9 | 11 | ||
| 21 Howto Blog | Blog Post | claude-sonnet-5-5 | 436 | 3 | 12 | ||
| 22 News Article | News Article | claude-sonnet-5-5 | 444 | 12 | 10 | ||
| 23 Discussion Post | Discussion Board | gemini-3-8-flash | 250 | 6 | 10 | ||
| 24 Discussion Post | Discussion Board | claude-sonnet-5-5 | 274 | 7 | 10 | ||
| 25 Cover Letter | Application Essay | gemini-3-8-flash | 369 | 7 | 14 | ||
| 26 Listicle Blog | Blog Post | gpt-6-sol | 409 | 10 | 11 | ||
| 27 Cover Letter | Application Essay | claude-sonnet-5-5 | 414 | 4 | 13 | ||
| 28 Personal Statement | Application Essay | gpt-6-sol | 357 | 8 | 12 | ||
| 29 News Article | News Article | gemini-3-8-flash | 420 | 9 | 11 | ||
| 30 Argumentative Essay | Academic Essay | gemini-3-8-flash | 431 | 8 | 13 |
"Passed" counts the ranked tools whose rewrite of that prompt at least 5 of the 6 detectors scored as human-written (0.50 or above); "Failed" counts those flagged by at least one detector that scored them; "Hardest" is the single detector that flagged the most rewrites of that prompt.
Recordings
Every tool was run in a recorded sitting. Each recording opens here from the start; the outputs pages jump to the exact moment a prompt was run.
-
WriteHuman 11:46 · 30 prompts · Oct 1, 2026 -
StealthGPT 38:33 · 30 prompts · Oct 1, 2026 -
Undetectable.ai 10:13 · 30 prompts · Oct 1, 2026 -
Clever AI Humanizer 18:04 · 30 prompts · Oct 1, 2026 -
Humanize AI Pro 10:55 · 30 prompts · Oct 1, 2026 -
AI Humanize io 9:42 · 30 prompts · Oct 1, 2026 -
Super Humanizer 4:03 · 30 prompts · Oct 1, 2026 -
Stealth Writer 6:12 · 30 prompts · Oct 1, 2026 -
HIX Bypass 11:10 · 30 prompts · Oct 1, 2026 -
Walter Writes 14:38 · 30 prompts · Oct 1, 2026 -
SupWriter 10:12 · 30 prompts · Oct 1, 2026 -
Phrasly 12:41 · 30 prompts · Oct 1, 2026 -
Humbot 37:09 · 30 prompts · Oct 1, 2026 -
Grammarly 4:56 · 30 prompts · Oct 1, 2026