Test log
Quetext test data
Raw results for the Quetext review. The verdict is in the review.
- Tested
- 6 November 2026
- Tester
- Miles Foster
- Account
- Free demo account, signed up by RankDude, nothing paid to the brand
- Tests
- 8
- Screenshots
- 8
- Method
- Published methodology
- Environment
- Google Chrome on desktop
Results
| ID | Test | Key measurement | Score |
|---|---|---|---|
| T01 | Accuracy on AI-Written Text | AI passages caught: 5 of 5 | 5/5 |
| T02 | False Positives on Human Text | Human passages flagged as AI: 0 of 5 | 5/5 |
| T03 | Mixed & Lightly-Edited Text | Mixed passages flagged as containing AI: 2 of 2 | 5/5 |
| T04 | Non-English Text | Passages correct: 4 of 4 | 5/5 |
| T05 | Document & File Support | Ways in verified: 1 of 10 | 3/5 |
| T06 | Score Clarity & Evidence | Points met: 6 of 10 | 3/5 |
| T07 | Scan Speed | Median per scan: 2.7 s | 5/5 |
| T08 | Pricing & Free-Tier Limits | Free AI words shown: 2,000 | 4/5 |
| Overall (in the review) | 4.4/5 | ||
Accuracy on AI-Written Text
5/5Tested- Method
- Five AI-written passages of 78 to 91 words (remote work, the Industrial Revolution, sleep, a cover letter, electric cars) were pasted once each; the first verdict counted, with 50 percent AI as the line.
- AI passages caught
- 5 of 5
- Lowest AI score
- 100% AI
- Remark
- Scale 5: 47 to 50 of 50 caught. 5 of 5 is 100 percent, so the grade is 5; the sample is five passages, not fifty.
Raw notes
Five AI-written passages of 78 to 91 words (remote work, the Industrial Revolution, sleep, a cover letter, electric cars) were pasted once each; the first verdict counted, with 50 percent AI as the line.
All five scored 100% AI, with the verdict "Our detector found this text is likely AI" and every sentence shaded as an AI match.
A sixth and seventh AI passage in Spanish and German also scored 99.99% and 99.59% AI (see the non-English test).
- Five passages from one model (Claude), at default settings, not 50 from six models.
False Positives on Human Text
5/5Tested- Method
- Five passages from books published before 1900 (Pride and Prejudice, Walden, On the Origin of Species, Moby-Dick and the Autobiography of Benjamin Franklin) were pasted once each, so any AI flag would be a false positive.
- Human passages flagged as AI
- 0 of 5
- Highest human-passage AI score
- 0.15%
- Remark
- Scale 5: at most 1 of 50 flagged. 0 of 5 flagged is 0 percent.
Raw notes
Five passages from books published before 1900 (Pride and Prejudice, Walden, On the Origin of Species, Moby-Dick and the Autobiography of Benjamin Franklin) were pasted once each, so any AI flag would be a false positive.
Every verdict read "likely Human". The AI Scores in the Reports list were 0.01%, 0.01%, 0.02%, 0.09% and 0.15%, and no sentence was marked as AI.
The two non-English human passages (Don Quijote, Les Miserables) scored 0.1% and 0.64% AI.
- Old literary text is far from the student and web writing that detectors wrongly accuse; a clean result here is a minimum. Five passages, not fifty.
Mixed & Lightly-Edited Text
5/5Tested- Method
- Two passages each joined a human paragraph (from Great Expectations and A Tale of Two Cities) to an AI paragraph, one with the AI part last and one with it first, and were scanned once.
- Mixed passages flagged as containing AI
- 2 of 2
- AI Scores
- 50% and 48.28%
- Remark
- Counted as flagged because the verdict said Mixed and the right sentences were marked. Scale 5 is 17 of 20 with accurate highlights; 2 of 2 is 100 percent.
Raw notes
Two passages each joined a human paragraph (from Great Expectations and A Tale of Two Cities) to an AI paragraph, one with the AI part last and one with it first, and were scanned once.
Both came back with the verdict "likely Mixed" and AI Scores of 50% and 48.28%. In both, the two AI sentences were the ones shaded and listed as AI matches, and the human sentences were left plain.
- Two passages, not twenty. The AI-draft-with-human-edits kind was not run.
Non-English Text
5/5Tested- Method
- Four passages were scanned once: an AI passage in Spanish, an AI passage in German, a human Spanish passage (Don Quijote) and a human French passage (Les Miserables).
- Passages correct
- 4 of 4
- Human passages flagged
- 0
- Remark
- Scale 5: 22 to 24 of 24 correct with at most one human passage flagged. 4 of 4 is 100 percent.
Raw notes
Four passages were scanned once: an AI passage in Spanish, an AI passage in German, a human Spanish passage (Don Quijote) and a human French passage (Les Miserables).
The AI passages scored 99.99% (Spanish) and 99.59% (German) AI. The human Spanish passage scored 0.1% and the human French passage 0.64%.
No human passage was flagged.
- Four passages, three languages. Chinese was not run.
Document & File Support
3/5Tested- Method
- Each way in was tried on the free plan: paste, a Word file, the bulk buttons, a web address, then the cap, extension, API and export points were checked.
- Ways in verified
- 1 of 10
- Remark
- The checklist could not be finished because the upload failed on my test file and several points sit behind a paid plan, so the test carries the default grade of 3 and says why. By the scale alone, 1 verified point would be a 1.
Raw notes
Each way in was tried on the free plan: paste, a Word file, the bulk buttons, a web address, then the cap, extension, API and export points were checked.
Worked end to end: paste. That is 1 of 10 verified.
A Word file built by a script was accepted by the upload box (a green tick) twice, at 56 words and at 82 words, but the scan stopped each time with "AI Detection requires a minimum of 50 words submitted". I could not tell whether the fault was my file or the product, so the upload point is not counted.
Locked or not run: Bulk File Scan and Bulk URL Check show a Premium Feature box; the PDF export says it needs a paid plan; the web address tab is marked beta and was not run, because a page long enough would have spent more than 85 percent of the allowance; the Chrome extension was not installed; the API page shows an empty key list and a prepaid wallet, with no key created. The free plan says each check is up to 1,000 words, so a 2,000-word scan was not possible.
- A PDF and a text file were not tried because the upload box names Word files. A real Word document, rather than a script-built one, might scan.
Score Clarity & Evidence
3/5Tested- Method
- Each of the ten points was checked on the scans already run, with one passage scanned twice for repeatability.
- Points met
- 6 of 10
- Remark
- Scale 3: 6 or 7 of 10 points.
Raw notes
Each of the ten points was checked on the scans already run, with one passage scanned twice for repeatability.
Met: a plain verdict sentence (likely AI, Mixed or Human); a percentage; sentence highlighting, with a per-sentence "100% AI" tag; a scan history (the Reports list, with title, AI Score and time); repeatability (the same passage scored 100% AI twice, with four AI sentences both times); no upsell blocking the result. That is 6 of 10.
Missed: a stated confidence band; a share link or a download (the PDF report is locked); a stated limit of the detector; and a readable explanation, because I did not open the small information tips next to the score. A guided-tour pop-up also opened over the first result until I closed it.
- Repeatability used two scans, not three, to stay inside the allowance.
Scan Speed
5/5Tested- Method
- Sixteen of the 17 scans were timed from pressing Check AI to the AI Score on screen, checking ten times a second.
- Median per scan
- 2.7 s
- Slowest scan
- 3.1 s
- Remark
- Scale 5: a median under 5 seconds.
Raw notes
Sixteen of the 17 scans were timed from pressing Check AI to the AI Score on screen, checking ten times a second. The first scan was done by hand and not timed.
Median 2.7 seconds, fastest 2.5, slowest 3.1. No scan failed or queued.
- Passages of 73 to 120 words; a long document takes longer. Free-plan speed only.
Pricing & Free-Tier Limits
4/5Tested- Method
- The free allowance was used until I reached 81 percent of it; the plans box in the app and the public pricing page were read on the test date.
- Free AI words shown
- 2,000
- Cost of 1,000 words on Essential
- about 15 cents
- Remark
- Scale 4: a usable free tier and a paid plan from $10 to $19.99 that lifts the limits and adds files and bulk. The single-feature plan is cheaper but does not add bulk.
Raw notes
The free allowance was used until I reached 81 percent of it; the plans box in the app and the public pricing page were read on the test date.
Free: the app showed 2,000 words for the AI detector, no card, and a Google sign-in. The pricing page says each check is up to 1,000 words. I could not see whether the 2,000 words come back, because I stopped before the limit.
Essential is $14.99 a month, or $8.25 a month billed yearly, for 100,000 words a month with bulk uploads of 20 files. That is about 15 cents for 1,000 words on the monthly price. Professional is $29.98 a month for 200,000 words and an API.
The in-app plans box also offers single-feature plans for the AI detector or the plagiarism checker alone, at 50,000 words a month.
- No plan was bought; checkout was not opened.
Coverage
Tested
- 17 scans: 5 AI passages, 5 human passages from books published before 1900, 2 mixed passages, 4 non-English passages and one repeat
- Time from pressing Check AI to the verdict, for 16 of the 17 scans
- The upload box with two Word files, the bulk file and bulk URL buttons, the PDF export and the Reports list
- The in-app plans box and the public pricing page, read on the test date
- The Trustpilot page read in the same browser
Not tested or limited
- The free allowance paid for 17 short passages of 73 to 120 words, not 50 + 50 + 20 + 20 + 24 full passages
- Resistance to humanisers and AI model coverage were not run: no humaniser account was bought and every AI passage was written by one model
- Every human passage is from an old book, which is easier to tell from AI than a modern essay
- Chinese was left out of the non-English test to save words
- Two Word files made by a script were refused at the scan with a 50-word minimum message, so file upload could not be confirmed; a web address, a PDF and a 2,000-word scan were not tried
- No plan was bought: bulk checks, the PDF export and the API were seen locked or empty, not run
Still to test
- The other 45 AI and 45 human passages on a paid plan
- Resistance to humanisers and paraphrasers
- AI model coverage across six models
- A real Word document, a PDF and a web address
- A 2,000-word scan and a bulk batch