S SoftMaxx Peptides ← All articles
Comparison · QOVES

QOVES vs ChatGPT: can a prompt replace a facial analysis?

A chatbot will happily rate a selfie. QOVES published data on how those ratings compare with human ones. Here is what it shows, what a prompt cannot do, and where each option fits — every figure quoted and dated.

Published 2026-09-17 · Last reviewed 2026-09-25 · ~7 minute read · Editorial standards

A ChatGPT prompt can rank faces roughly the way people do, but it cannot rate them the way people do, and it does not measure anything. That is the finding of QOVES's own research page, Do AI models rate faces like humans? (labelled 2026 / Summer, read 17 September 2026): "AI models do not judge facial attractiveness like humans; they rate almost everyone above average and never give the lowest scores. However, models can rank faces similarly to how people do." On a 1–7 scale the human average was 3.02; ChatGPT averaged 4.41, Claude 4.53, Gemini 4.69 and Grok 5.21.

So the honest answer to "QOVES vs ChatGPT" is that they are different kinds of thing. A prompt gives you a fast, flattering opinion. QOVES sells a measured report reviewed by people, for $150 a year and a wait of up to 28 days. This page sets out what the data says, what a prompt structurally cannot do, and which option fits which need.

1. What QOVES tested, in their words

The study used the Face Research Lab London Set: "102 neutral, front-facing portraits normalized for pose, lighting, and framing. 2,513 people rated each on a 1–7 attractiveness scale." Then "four commercial models (Claude, ChatGPT, Gemini, and Grok) rated the same faces one at a time, with no memory of the faces they had already seen. Each model rated every face repeatedly," and the repeated ratings were averaged into one score per face. (qoves.com/research, read 2026-09-17.)

RaterMean rating (1–7)
Humans (2,513 raters)3.02
ChatGPT4.41
Claude4.53
Gemini4.69
Grok5.21

Two more lines from the same page matter: "No AI model rated anyone a 1 out of 7, and only Grok gave the highest rating." The models compress everyone into the upper middle of the scale.

2. Ranking is not rating

The same page reports rank agreement between each model and the average human of Spearman ρ between .58 and .76 (Claude: ρ = .76, 95% interval .67–.83), and comments: "Rank agreements between .58 and .76 are not trivial. All models, except Grok, order the faces in terms of attractiveness close to how humans do."

Read together, the two results say something specific. Ask a chatbot which of two photos of you is stronger and the answer carries real signal. Ask it for a score out of 10 and the number is inflated by roughly one and a half to two points on a seven-point scale, with the bottom of the scale never used. A rating you cannot fail is not a rating; it is reassurance.

3. What a prompt structurally cannot do

4. Can't I just use ChatGPT or Claude? QOVES's own answer

QOVES answers the question directly in the FAQ of the landing page its September 2026 ads point to (welcome.qoves.com/potential; the answer below as read 25 September 2026). Their wording is "Can't I just do this with Chat GPT or Claude?" In summary, the answer says:

Our read. The measurement point is right, and it is the same point QOVES's own study makes with numbers in the sections above: a prompt returns prose, not landmarks. The golden-ratio point agrees with our science page, which does not use the golden ratio as a basis for the score. The rest is positioning: the landing page counts "100+ aesthetic tests" while the QOVES homepage says "more than 160", and "a different category entirely" is a sales line, not a finding. If a free chatbot answer is enough for your question, QOVES's own FAQ agrees that it is.

5. A QOVES-style ChatGPT or Claude prompt, and what it cannot measure

People search for a "QOVES ChatGPT prompt" or "QOVES Claude prompt". There is no official one. If you want the most useful answer a chatbot can give, ask it to describe and to flag its own uncertainty rather than to rate you. Use a front-facing photo taken at eye level, at arm's length, in even light, with a neutral expression:

Copy this prompt

I'm sharing a front-facing photo taken at eye level, at arm's length, in even light, with a neutral expression. Please do not rate my attractiveness or give me a score. Instead, describe what you can see, and for each point say how confident you are and what in the photo (angle, lens distance, lighting, expression) could make it wrong:

  1. Facial thirds: hairline to brow, brow to the base of the nose, base of the nose to the chin. Do they look roughly equal, or does one look longer?
  2. Eye area: do the outer corners of the eyes sit higher, level with, or lower than the inner corners? How much upper eyelid is visible?
  3. Jaw and chin: how defined does the jawline look in this photo, and does the chin look balanced with the rest of the lower third?
  4. Skin: visible texture, redness or under-eye shadow, and which of these the lighting could be causing.
  5. Hair and brows: how the current hairstyle and brow shape frame the face.

Then list up to five low-cost, non-surgical changes (grooming, hairstyle, brows, skincare, sleep, posture) ranked by likely visible impact, and tell me which of your observations would need a real measurement to confirm.

What this prompt cannot measure. No landmarks are placed, so any number the chatbot gives you — a canthal tilt in degrees, a ratio, a percentage — was not measured. It cannot correct for lens distortion or head tilt, which move facial proportions more than most routines do. It keeps no baseline, so next month's answer is a fresh opinion, not a comparison. And the provider may hedge or decline, by policy, and can change that without notice. We have not tested this prompt across models; treat what it returns as a description to check, not a result.

If you want a person to write the plan, that is QOVES — what it costs and whether it is worth it.

6. Where SoftMaxx AI sits (ours, so read it as such)

SoftMaxx AI is AI, not a human analyst, and it is not a substitute for what QOVES sells. It differs from a bare prompt in two ways that the QOVES study makes relevant. First, geometry is measured rather than described: 478 landmark points are computed in your browser and sent to our backend as numeric ratios, as the methodology page sets out. Second, scoring is calibrated "so that population average sits near 5.0/10" — and you can check that against the dated snapshots of the full score distribution published here. Low scores are used. That is the property the chatbots in the QOVES study lacked.

The limits are just as real: a vision model still reads the photo for everything geometry cannot capture, no person reviews your result, and the same methodology page says plainly that it "does not replace clinical evaluation."

7. Which to use for what

8. What this page cannot tell you

The study is QOVES's own, published on its site; we found no journal version, and a vendor has an interest in showing that a free chatbot is not a replacement for its paid service. The face set is 102 neutral studio portraits, which is not how anyone photographs themselves for a prompt. We did not run prompts ourselves, so nothing here describes how a specific model will respond to your photo today. And attractiveness ratings, human or machine, describe agreement among raters — not worth, and not a diagnosis. If rating yourself is causing distress, that is a reason to stop and talk to someone, not a reason to find a more accurate rater.

9. Common questions

Can ChatGPT do a QOVES-style facial analysis?

It can describe a face and rank photos roughly the way people do, but it does not landmark or measure anything and it is not reviewed by a person. QOVES's own study found ChatGPT's average rating was 4.41 out of 7 against a human average of 3.02 on the same 102 faces, with no model ever giving the lowest score.

Is there a QOVES prompt for ChatGPT or Claude?

There is no official QOVES prompt. This page gives a descriptive prompt that asks the chatbot to describe your thirds, eye area, jaw, skin and framing and to flag its uncertainty instead of rating you. It cannot reproduce the product: QOVES says it maps 521 facial points, runs more than 160 tests and has every analysis reviewed by its team, while a prompt returns an unmeasured opinion.

What does QOVES say about using ChatGPT or Claude instead?

On the landing page its September 2026 ads point to, QOVES answers that chatbots offer only general guidance: they cannot place landmarks, measure skin texture or run its 100+ aesthetic tests, they lean on outdated frameworks like the golden ratio, and AI-edited previews change more than the feature asked about. It says it uses tools like Claude only to help write up findings, and that ChatGPT is a reasonable starting point for quick, free questions.

How accurate is AI at rating attractiveness?

In QOVES's study the four models agreed with human rank order at Spearman ρ .58 to .76, which is meaningful, but their absolute ratings were inflated: means of 4.41 to 5.21 on a 1–7 scale versus 3.02 for 2,513 human raters.

Why do chatbots rate everyone above average?

The QOVES page reports the pattern — "they rate almost everyone above average and never give the lowest scores" — without proving a cause. Provider policies against critiquing people's appearance are one plausible contributor; Anthropic's usage policy, for example, prohibits using its models to critique anyone's body shape or size.

Will Claude or ChatGPT refuse to rate my face?

Sometimes. It depends on the provider's policy and the wording, and it can change without notice. Anthropic's published usage policy prohibits promoting unhealthy or unattainable beauty standards.

Is SoftMaxx AI just ChatGPT with a prompt?

No. Facial geometry is measured from 478 landmarks computed in your browser, and scoring is calibrated so the population average sits near 5 out of 10 — the dated distribution is published on our score-distribution page. It is still AI, with no human reviewer, and it does not replace clinical evaluation.

What is the cheapest way to get a real baseline?

A free measured scan: SoftMaxx AI's gives an overall score, four pillar bands and your top priority, and you can repeat it next month; the category sub-scores are Pro. A chatbot is free too, but its score is inflated and not repeatable as a series. QOVES costs $150 a year and returns a human-reviewed report within 28 days.

Keep reading