--- title: "Autism Spectrum Quotient (AQ-10): Score the Screener" url: "https://www.ellomind.com/ai-tools-for-psychologists/scales/autism-spectrum-quotient/" description: "Autism Spectrum Quotient (AQ-10) screener for clinicians: score the 10 items, with the scoring key, the referral cut-off and a ready-made AI prompt to score de-identified responses. Free, India-first." --- Autism screening # Autism Spectrum Quotient (AQ-10) Self-report · 10 items · 2 min Score the AQ-10, the brief, NICE-recommended screening version of the Autism Spectrum Quotient for adults. Ten items, shown in full, with an AI prompt to score de-identified responses and apply the cut-off. Copy prompt Download as .md **De-identify first.** The prompt runs in your own AI assistant. Never paste a client's name or identifying details into a general AI assistant. ## What it measures The AQ-10 is a ten-item screening questionnaire drawn from the longer 50-item Autism Spectrum Quotient. It is recommended by NICE as a quick first step when autism is a possibility in adults with average or above-average intelligence. It is a screen, not a diagnostic tool. A score at or above the cut-off suggests that a full diagnostic assessment may be warranted; it does not, on its own, indicate autism. ## The AQ-10 items How much does the client agree with each statement? 1. I often notice small sounds when others do not. 2. I usually concentrate more on the whole picture, rather than the small details. 3. I find it easy to do more than one thing at once. 4. If there is an interruption, I can switch back to what I was doing very quickly. 5. I find it easy to read between the lines when someone is talking to me. 6. I know how to tell if someone listening to me is getting bored. 7. When I'm reading a story, I find it difficult to work out the characters' intentions. 8. I like to collect information about categories of things (e.g. types of car, bird, train, plant). 9. I find it easy to work out what someone is thinking or feeling just by looking at their face. 10. I find it difficult to work out people's intentions. **Response options:** Agree (1), Disagree (0). ## Scoring and interpretation The client marks how much they agree with each statement. Each item scores one point in the autism-consistent direction; the AI prompt handles which items score for agreement and which for disagreement. The total ranges from 0 to 10. A score of 6 or more is the usual threshold to consider referral for a full autism assessment. Use it as a prompt for further assessment, never as a diagnosis. | Score | Interpretation | | ----- | ------------------------------------------------------ | | 0–5 | Below the referral threshold | | 6+ | At or above the threshold — consider a full assessment | A four-point agree/disagree response is collapsed to a single point per item. Items 2, 3, 4, 5, 6 and 9 score for disagreement (the AI prompt applies these). A screen, not a diagnosis. ## Score it with AI A ready-made prompt that turns any AI assistant into a scorer for the AQ-10\. Paste it in, add the client's de-identified responses, and it computes the score and interpretation. Copy it, or download it to save as a reusable prompt. 1. 1 Copy the prompt below, or download it as a file. 2. 2 Open your AI assistant (Claude, ChatGPT, Gemini, or any LLM). 3. 3 Paste the prompt, then add the client's de-identified responses. 4. 4 Review the score and interpretation before you use them. You are a careful scoring assistant for the Autism Spectrum Quotient (AQ-10), helping a qualified professional. You are a scoring aid, not a clinician: you do not diagnose or recommend treatment. Ground rules: - Use ONLY the items, response options and cut-offs given below as the source of truth. Do not rely on any version of this scale from memory; scales have variants and remembered items, scoring or cut-offs may be wrong. - If anything I paste could identify a client, stop and ask me to de-identify it before scoring. - Never guess, impute, average, or fill in a missing or unclear response. Scale: self-report measure, 10 items. Each item is scored: 1 = Agree; 0 = Disagree. Items: 1. I often notice small sounds when others do not. 2. I usually concentrate more on the whole picture, rather than the small details. 3. I find it easy to do more than one thing at once. 4. If there is an interruption, I can switch back to what I was doing very quickly. 5. I find it easy to read between the lines when someone is talking to me. 6. I know how to tell if someone listening to me is getting bored. 7. When I'm reading a story, I find it difficult to work out the characters' intentions. 8. I like to collect information about categories of things (e.g. types of car, bird, train, plant). 9. I find it easy to work out what someone is thinking or feeling just by looking at their face. 10. I find it difficult to work out people's intentions. Reverse-scored items: 2, 3, 4, 5, 6, 9. For each of these, replace the response r with (that item's own maximum value − r), and show the reversed value. Interpretation (ranges are inclusive; work out from these bands whether a higher score means more or less of the construct): - Total 0 to 10: 0–5 Below the referral threshold; 6+ At or above the threshold — consider a full assessment. When I give the client's de-identified responses, work in this order: 1. Parse them as item → value and restate the table so I can check it. If I give option labels, the client's words, or a finer scale than the options above, map each to the listed values and show the mapping. 2. Validate before scoring: confirm there are exactly 10 responses, each within its allowed range. If any are missing, extra, duplicated, out of range, or ambiguous, STOP and tell me what is wrong. Do not score a partial or invalid set. 3. Show your work: list the value used for each item (after any reverse-scoring), then add them explicitly. Add them to reach the total. Use only the numbers above. 4. Report, in this order: - the total score; - the severity band, quoting the exact range it falls in; - one or two sentences on what the score means on this scale; - this caveat: A four-point agree/disagree response is collapsed to a single point per item. Items 2, 3, 4, 5, 6 and 9 score for disagreement (the AI prompt applies these). A screen, not a diagnosis. - a reminder that the AQ-10 is a screening or rating aid, not a diagnosis, to be read within a full clinical assessment. 5. Re-check the arithmetic before finalising, and do not add a diagnosis, formulation or treatment plan unless I ask separately. Here are the de-identified responses: Copy prompt Download as .md Before you rely on the score * **Check the maths yourself.** AI assistants can still add up wrong or misapply a rule. The prompt makes the assistant show each item's value and the sum, so glance over that working, and re-total anything you will act on. * **Confirm it used this scale.** Check that the items, response values, reverse-scoring and cut-offs it used match this page, not a different or outdated version the model recalled. * **Watch for missing or odd inputs.** The prompt is told to stop rather than guess a missing or out-of-range response. If it scores anyway, treat the result as unreliable and re-check your inputs. * **Act on critical items regardless of the total.** Respond to risk indicators, such as a self-harm item, on their own merit, even when the overall score looks low. * **De-identify first, every time.** The assistant runs in your own account, outside ElloMind. Never enter a client's name or identifying details. * **It is a screening aid, not the decision.** The score supports your clinical judgement within a full assessment. It does not diagnose, and it does not decide. ## Use the score in your notes Take the score into a de-identified write-up with one of the free AI tools. [Formulation Case formulation (5Ps and CBT)](/ai-tools-for-psychologists/case-formulation/) [Report writing Referral letter](/ai-tools-for-psychologists/referral-letter/) ## Citation and sources Allison, C., Auyeung, B., & Baron-Cohen, S. (2012). Toward brief 'red flags' for autism screening: the short Autism Spectrum Quotient (AQ-10). Journal of the American Academy of Child & Adolescent Psychiatry, 51(2), 202-212. The AQ-10 is freely available for clinical and research use; developed at the Autism Research Centre, University of Cambridge. * [Autism Spectrum Quotient (overview)](https://en.wikipedia.org/wiki/Autism-spectrum%5Fquotient) — Wikipedia ## Frequently asked questions What is a positive AQ-10 score? + A score of 6 or more out of 10 is the usual threshold to consider referring an adult for a full autism assessment. It is a screening cut-off, not a diagnosis. How is the AQ-10 different from the full AQ? + The AQ-10 is a ten-item short version of the 50-item Autism Spectrum Quotient, selected for screening. NICE recommends it as a quick first step. Can the AQ-10 diagnose autism? + No. It only flags whether a fuller diagnostic assessment may be warranted. Diagnosis requires a comprehensive evaluation by a qualified professional. Does ElloMind see the client's data? + No. The prompt runs in your own AI assistant, and ElloMind never sees it. De-identify client information first. ## More scales [Depression Patient Health Questionnaire-9 (PHQ-9)](/ai-tools-for-psychologists/scales/phq-9-depression-scale/) [Anxiety Generalised Anxiety Disorder-7 (GAD-7)](/ai-tools-for-psychologists/scales/gad-7-anxiety-scale/) [Depression · Anxiety · Stress Depression Anxiety Stress Scales (DASS-21)](/ai-tools-for-psychologists/scales/dass-21/) [Depression Hamilton Depression Rating Scale (HAM-D)](/ai-tools-for-psychologists/scales/hamilton-depression-rating-scale/) A screening and rating aid for qualified professionals, not a diagnosis or a substitute for clinical judgement. Interpret every score within a full assessment. Never paste identifiable client data into a general AI assistant. If a client is in crisis, contact a [crisis helpline](/crisis-helpline/) right away. [Back to all scales](/ai-tools-for-psychologists/scales/)