中文（繁體）
中文（简体）
English
IB Mathematics AI SL Paper 2: Modelling in Context
Maths: calculator long answers and modelling in context
AI SL Paper 2 allows the calculator, runs long and stays in context. Marks sit at the step where the context becomes mathematics, and in the sentence that carries the answer back to the situation. Correct arithmetic with no unit and no conclusion usually earns half.
How is IB Mathematics AI SL Paper 2 assessed, and what does each part carry?
Paper 1 (short-response, technology allowed): Compulsory short-response questions; 80 marks (SL 40%); Paper 2 (this paper, GDC required): Compulsory extended-response questions in real contexts; 80 marks (SL 40%); Exploration (internal assessment): 15 recommended hours within the 150-hour course (20%)
Assessment at a glance (2027)
| Component | Content | Weighting | Duration |
|---|---|---|---|
| Paper 1 (short-response, technology allowed) | Compulsory short-response questions; 80 marks | SL 40% | 1.5 h |
| Paper 2 (this paper, GDC required) | Compulsory extended-response questions in real contexts; 80 marks | SL 40% | 1.5 h |
| Exploration (internal assessment) | 15 recommended hours within the 150-hour course | 20% | during the course |
IB Maths AI SL Paper 2 drilling technique: write down what you need and which GDC function you will use before touching the keys, and always translate the answer back into the context (36.2 years becomes “about 36 years”; 0.292 becomes “29.2% take neither”). Percentage change, conditional probability and sample standard deviation are the three most common mark losses – three significant figures and units every time.
What each paper is actually testing
| Paper | Drill focus | How marks are lost |
|---|---|---|
| Paper 1 (short-response, technology allowed) | core skills and graph reading | Calculation starts before the variables are defined: the stem says cost rises with output and the answer gives a number, losing the model and the definitions the marks were for. |
| Paper 2 (this paper, GDC required) | state the model and assumptions, then compute and interpret | Every calculator digit is copied, rounding ignores the accuracy demanded, or rounding happens too early and the final answer drifts outside the accepted range. |
| Exploration (internal assessment) | model real data and reflect on the limits | Context questions stop at the number: t = 4.2 with no sentence saying roughly four years, while the mark scheme explicitly asks for the answer in context. |
What is each IB Mathematics AI SL Paper 2 paper really testing, and what should you drill?
Paper 1 (short-response, technology allowed): core skills and graph reading; Paper 2 (this paper, GDC required): state the model and assumptions, then compute and interpret; Exploration (internal assessment): model real data and reflect on the limits
Drill order: by topic, then by year, then the mark scheme
| Step | What you do | Why |
|---|---|---|
| 1. By topic | Work through each topic, starting with the paper that allows least help (no calculator / closed book) | Exposes what is genuinely not understood |
| 2. By year | Whole papers to time, one or two a week | Trains pace, stamina and question selection |
| 3. Mark scheme | Go through the marking scheme question by question and log the scoring steps you missed | Most lost marks are written wrong, not thought wrong |
Should drilling go by topic first or by year?
By topic first, then whole papers by year, then the mark scheme. The first third of the time goes topic by topic (8-10 years of the same topic back to back), the middle switches to timed whole papers, and the last fortnight only redoes the recurring errors from your log.
A 12-week drilling timetable
| Week | Phase | What to do |
|---|---|---|
| Weeks 1-3 | By topic: foundation | Topic by topic, starting with the easiest marks, building habits and recall |
| Weeks 4-6 | By topic: core | 8-10 years of the same topic back to back, errors classified by topic |
| Weeks 7-8 | By topic: advanced and electives | Elective and higher-order topics, now under time pressure |
| Weeks 9-10 | By year: timed papers | One full paper a week, timed, no reference materials |
| Week 11 | Mark scheme work | Question by question against the marking scheme; list the scoring steps you omitted |
| Week 12 | Plug holes and simulate | Only the recurring errors from your log, then one full exam simulation |
Subject-specific weighting for this timetable: Weeks 1-3: functions and models. Define the variable, write the relationship, substitute last, and state one limitation of every model.\nWeeks 4-6: statistics and probability. Graph, centre and spread from one data set; test independence before any probability calculation.\nWeeks 7-9: calculus and financial maths. Optimisation runs model, derivative, endpoints; finance starts by matching present value to the number of periods.\nWeeks 10-12: whole papers to time; redo only the missing-conclusion and rounding errors.
Use it properly: this is not a checklist to finish. Every week must keep time for redoing errors, or from week 9 you will be repeating the same batch.
Pacing
| Paper | Time | Suggested split |
|---|---|---|
| Paper 1 (short-response, technology allowed) | 1.5 h | short, single-step questions |
| Paper 2 (this paper, GDC required) | 1.5 h | 10 questions at about 8 min each, 10 min to check |
| Exploration (internal assessment) | during the course | work in stages: fix the topic before collecting data |
How should the time be split inside each IB Mathematics AI SL Paper 2 paper?
Paper 1 (short-response, technology allowed): short, single-step questions; Paper 2 (this paper, GDC required): 10 questions at about 8 min each, 10 min to check; Exploration (internal assessment): work in stages: fix the topic before collecting data
The drilling mistakes that cost the most marks
| Mistake | What it looks like | What actually happens | Instead |
|---|---|---|---|
| Answer not returned to context | Writing just 36.2 or 0.292 | All interpretation marks vanish | “about 36 years”, “29.2% take neither” |
| Wrong standard deviation | Copying σ from the GDC | Sample data needs s, so the number disagrees | Tell s from σ and use s for samples |
| Percentage change error | Writing 9382 ÷ 8000 | Answers 1.17 instead of 17.3% | Subtract the original, divide by the original, times 100% |
| Wrong denominator for a conditional | P(physics | maths) as 30 ÷ 120 | Understates the probability by more than half | Divide by the given group only: 30 ÷ 70 |
The error log and the mark scheme
Three columns: the question and the answer given; the model and closing sentence the scheme wanted; and whether the loss was definition, rounding or the missing return to context. A missing conclusion earns the correct sentence copied once, since the same shape recurs.
How many years should you drill?
AI SL is a newer course, so published past papers are limited and By Year alone will not carry you. Work mainly from the official guide specimen items and original mocks, and use older papers from neighbouring courses for calculation and modelling while noting that calculator rules and mark emphases have changed.
How many years of past papers is enough?
AI SL is a newer course, so published past papers are limited and By Year alone will not carry you. Work mainly from the official guide specimen items and original mocks, and use older papers from neighbouring courses for calculation and modelling while noting that calculator rules and mark emphases have changed.
Frequently asked questions
Is this page a mock paper or a drilling guide?
This is the IB Mathematics AI SL Paper 2 drilling guide: assessment structure, drill order, a 12-week timetable, pacing, common mark losses and the error-log method. For questions with answers, use the IB Mathematics AI SL Paper 2 mock papers linked under Related.
By topic or by year first?
By topic. Eight to ten years of the same topic back to back is what exposes repeating errors; going straight to whole papers just repeats the same batch under time pressure.
How should the error log be written?
Do not copy out questions. Per error record four things: question reference, which step failed (concept, wording, calculation), what the mark scheme requires, and the correct action next time.
Can the calculator replace hand work?
No. It handles arithmetic only; the model, the definitions and the choice of method must appear on paper, because method marks are awarded for the written relationship, not for key presses.
How many figures should an answer carry?
Three significant figures unless the question says otherwise. Keep full precision in the calculator and round only at the end, then attach the unit.
Official references
| Resource | What to use it for |
|---|---|
| IB mathematics curriculum page (IBO) | Confirm the Paper 1-2 marks and weighting |
| IB Maths AI SL Paper 1 mock | short-response modelling |
| IB Maths AA SL Paper 2 mock | the same-level GDC paper |
| Practice area | index of IB subject mocks |
Related: practice area · IB Maths AI SL Paper 1 · IB Maths AI HL · IB Maths AA SL Paper 2
Next step: find a tutor / register as a tutor
After drilling, the hard part is telling a conceptual error from a writing error. Tell us the year group, the school and your available times, and TutorZone will match you with a tutor who knows the HKEAA assessment requirements.
Demand for tutors in this subject is steady, and those who can explain the marking scheme and where marks are won are especially sought after. Register free; you pay only when a match succeeds.