August 2026 prompt evidence
Each of these 33 prompts was written by a frontier model, then handed to all 12 ranked humanizers, and every rewrite was submitted to 5 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 median score across the 5 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 | GPT-5.5 | 293 | 6 | 12 | ||
| 02 Argumentative Essay | Academic Essay | Gemini 3.5 Flash | 382 | 4 | 11 | ||
| 03 Howto Blog | Blog Post | Claude Sonnet 5 | 405 | 1 | 11 | ||
| 04 Listicle Blog | Blog Post | Claude Sonnet 5 | 396 | 5 | 9 | ||
| 05 Product Desc | Marketing Copy | Claude Sonnet 5 | 199 | 8 | 9 | ||
| 06 Cover Letter | Application Essay | Gemini 3.5 Flash | 359 | 2 | 12 | ||
| 07 Howto Blog | Blog Post | GPT-5.5 | 434 | 7 | 8 | ||
| 08 Howto Blog | Blog Post | Gemini 3.5 Flash | 399 | 6 | 10 | ||
| 09 Landing Copy | Marketing Copy | Gemini 3.5 Flash | 273 | 1 | 12 | ||
| 10 News Article | News Article | Gemini 3.5 Flash | 373 | 7 | 9 | ||
| 11 Lit Review | Academic Essay | GPT-5.5 | 430 | 6 | 9 | ||
| 12 Lit Review | Academic Essay | Claude Sonnet 5 | 389 | 8 | 6 | ||
| 13 News Article | News Article | Claude Sonnet 5 | 407 | 3 | 9 | ||
| 14 Discussion Post | Discussion Board | GPT-5.5 | 255 | 4 | 9 | ||
| 15 News Article | News Article | GPT-5.5 | 426 | 6 | 9 | ||
| 16 Product Desc | Marketing Copy | Gemini 3.5 Flash | 182 | 8 | 9 | ||
| 17 Landing Copy | Marketing Copy | Claude Sonnet 5 | 322 | 6 | 11 | ||
| 18 Discussion Post | Discussion Board | Claude Sonnet 5 | 260 | 6 | 9 | ||
| 19 Personal Statement | Application Essay | Gemini 3.5 Flash | 337 | 8 | 8 | ||
| 20 Discussion Post | Discussion Board | Gemini 3.5 Flash | 245 | 4 | 8 | ||
| 21 Business Email | Business Email | GPT-5.5 | 240 | 0 | 12 | ||
| 22 Listicle Blog | Blog Post | Gemini 3.5 Flash | 426 | 8 | 8 | ||
| 23 Personal Statement | Application Essay | GPT-5.5 | 359 | 9 | 6 | ||
| 24 Business Email | Business Email | Gemini 3.5 Flash | 236 | 1 | 12 | ||
| 25 Cover Letter | Application Essay | GPT-5.5 | 415 | 4 | 10 | ||
| 26 Personal Statement | Application Essay | Claude Sonnet 5 | 349 | 7 | 7 | ||
| 27 Argumentative Essay | Academic Essay | GPT-5.5 | 430 | 8 | 6 | ||
| 28 Business Email | Business Email | Claude Sonnet 5 | 273 | 0 | 12 | ||
| 29 Cover Letter | Application Essay | Claude Sonnet 5 | 402 | 1 | 11 | ||
| 30 Listicle Blog | Blog Post | GPT-5.5 | 433 | 6 | 10 | ||
| 31 Lit Review | Academic Essay | Gemini 3.5 Flash | 405 | 10 | 10 | ||
| 32 Argumentative Essay | Academic Essay | Claude Sonnet 5 | 424 | 5 | 11 | ||
| 33 Product Desc | Marketing Copy | GPT-5.5 | 184 | 7 | 8 |
"Passed" counts the ranked tools whose rewrite of that prompt at least 4 of the 5 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 11:56 · 33 prompts · Aug 1, 2026
-
Humanize AI Pro 10:58 · 33 prompts · Aug 2, 2026
-
Stealth Writer 9:00 · 33 prompts · Aug 1, 2026
-
HIX Bypass 9:21 · 33 prompts · Aug 1, 2026
-
Humbot 12:34 · 33 prompts · Aug 1, 2026
-
AI Humanize io 12:57 · 33 prompts · Aug 1, 2026
-
Phrasly 17:08 · 33 prompts · Aug 1, 2026
-
Undetectable.ai 14:46 · 33 prompts · Aug 1, 2026
-
Walter Writes 15:48 · 33 prompts · Aug 1, 2026
-
Super Humanizer 8:58 · 32 prompts · Aug 2, 2026
-
Grammarly 10:39 · 33 prompts · Aug 2, 2026
-
StealthGPT 16:24 · 33 prompts · Aug 1, 2026
-
NoteGPT not ranked this cycle 1:40 · 32 prompts · Aug 2, 2026