Home · Personal · Learning & Study · Exams & revision
As of 13 August 2026, AI can simulate a mock exam.
This still needs a person who signs their name to it.
Can you do it?
5 minutesto a draft.
30 minutesto something you’d act on.
Cost, all in£0
Skill neededchat-fluent
Who has to check ityou
What the alternative costsNo priced human alternative is listed in the supplied tool data.
If this goes wrong: the mock paper covers the wrong material or marks an open answer too generously, and you lose some revision time before correcting course.
What to actually do
Hand it to a person
The route this page recommends
A person who owns the outcome does this end to end, worth it when the failure is dear.
Do it yourself
Second choiceA chat interface, chat-fluent skill, and roughly 30 minutes until you can act on the result.
How to actually do it
- Open your course specification, revision notes and any official sample paper or mark scheme, then identify the exact subject, UK qualification, exam board and topics to practise.
- Choose the question types, number of questions, time limit and calculator or non-calculator conditions that match the real paper.
- Paste those details and any relevant specification or mark scheme into the prompt, removing personal information and copyrighted material you are not permitted to share.
- Start a fresh chat and paste the prompt, then answer each question under the stated time limit without asking for the solution first.
- When the mock ends, copy the score, marking points and weak-topic list into your revision notes.
- Compare disputed marks, model answers and topic coverage with the official specification or mark scheme, and correct any feedback that does not match them.
- Repeat the mock with different questions after revising the topics the feedback identified.
Prompt
Act as an exam simulator, not a tutor who gives away answers. Create and run a realistic mock exam using these details: - Subject: [subject] - UK qualification and level: [qualification and level] - Exam board: [exam board, or unknown] - Topics and specification points: [paste the topics or specification] - Exam format: [question types, calculator or non-calculator, written or oral] - Number of questions: [number] - Time limit: [time limit] - Difficulty: [difficulty] - Materials I have supplied: [paste any specification, sample questions or mark scheme] First, state the rules, total marks and time limit. Then give me one question at a time and wait for my answer. Do not reveal the answer or give hints unless I ask for a hint. Keep a running score, but do not mark an answer until I submit it. For each answer, show the marks awarded, the relevant marking points, what was correct, what was missing, and a concise model answer. Distinguish clearly between objective marking and judgement-based marking. If the supplied materials do not establish an answer or marking rule, say so instead of inventing one. At the end, give my score, topic-by-topic weaknesses, three priority revision actions and a short list of any answers or explanations I should verify against an official mark scheme or my course materials.
Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.
Use a tool built for this
The distant third
What it gets wrong
- It cannot guarantee that a generated paper matches the real exam board's wording, weighting or unseen content.
- It marks essays, extended writing and other open responses inconsistently when the mark scheme depends on interpretation.
- It can present an incorrect explanation or model answer confidently, so important feedback needs checking against your course materials.
- It cannot reproduce the pressure, invigilation, room conditions or accessibility arrangements of a formal UK examination.
- It cannot know which misconceptions you have unless your answers reveal them clearly.
Even on a YES, the friction has a name: judgement under ambiguity and verification cost.
How we scored this
Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.
| Axis | Score (0–2) |
|---|---|
| Output | 2 |
| Inputs | 2 |
| Verification | 1 |
| Liability | 2 |
| Effort delta | 2 |
| Total | 9 / 10 |
The methodology and its thresholds are published in full.
FAQ
- Can ChatGPT create a mock exam?
- Yes. It can create questions, run them one at a time, impose a time limit and give provisional marking and feedback. Give it the UK qualification, exam board and specification rather than only the subject name.
- Can AI mark my mock exam?
- It can mark many short-answer and calculation questions reasonably usefully, but essay and extended-response marks are provisional. Compare disputed marks and model answers with the official mark scheme or your teacher's guidance.
- Can AI make a mock exam from my syllabus?
- Yes, if you paste the relevant syllabus or specification and identify the topics, question types and level. Without that information, it may produce a plausible paper that does not match your course.
- Is it worth using AI for exam revision?
- Yes, as a source of extra practice and immediate questioning. Treat its paper and marking as revision aids, not as evidence of your likely grade, and verify important feedback against official materials.
Nearby answers
Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.
The newsletter
AI news, new answers and product picks, straight to your inbox.