Which course does AscentIQ cover?

IB Mathematics: Applications and Interpretation SL, completely — every topic in the syllabus, calibrated against real past papers and mark schemes. We cover one course properly rather than several superficially. Additional IB courses are on our roadmap; the Math AI SL depth is the standard we'll hold them to.

How does the marking actually work?

Your work is transcribed, then evaluated against the exercise's mark scheme one mark at a time. Each Method, Answer, and Reasoning mark is awarded or withheld with a written reason. Follow-through is applied, so an early error doesn't automatically cost you the marks that depend on it.

Can the AI get the maths wrong?

The maths isn't generated by AI. Every number in every exercise is computed deterministically before the AI is involved — the AI only writes the wording around values it's been given, and is blocked from producing numbers of its own.

Do I have to write by hand?

You don't have to, but the whiteboard is where the marking is worth most. Writing out formula, substitution, and answer lets each method mark be awarded or withheld on its own. Typing takes final answers only — quicker, but there's no working to mark, and nothing to review afterwards.

What do I need to use it?

A tablet with a stylus is the best experience — the whiteboard is built for it. A laptop or desktop works fully too. We wouldn't recommend a phone: the whiteboard needs more room than a phone screen gives it.

What's in the free trial?

Seven days of full access — every topic in the Math AI SL syllabus, unlimited generated exercises, and per-mark feedback on the work you write out. No card required to start — we'll ask for one on day 7 to continue.

What does "founding cohort" mean?

Founding cohort is open now and stays open based on demand, for as long as we're in this early stage of the platform. Founding members pay a reduced rate and keep it for as long as their subscription stays active, and they have direct input into what gets built next.

Subscriptions are annual and renew once a year. You can turn off renewal at any time from your account and keep access until the term ends.

IB Math AI SL · Topic 4

Statistics and probability

The largest topic in the course — eleven sections — and the one where the exam rewards language as much as calculation. Computing a p-value is routine; concluding from it in context is where grades separate.

What the syllabus covers

Eleven assessed sections, SL 4.1 to 4.11 — from sampling bias through to formal hypothesis tests.

SL 4.1SamplingPopulation versus sample, random sampling techniques and their effectiveness, bias and reliability of sources, and the interpretation of outliers.

SL 4.2Presentation of dataFrequency tables, histograms, box-and-whisker diagrams, and cumulative frequency graphs from which medians, quartiles and percentiles are read.

SL 4.3Central tendency and dispersionMean, median and mode; estimating the mean from grouped data; IQR and standard deviation, including how constant changes to the data move them.

SL 4.4Correlation and regressionScatter diagrams, lines of best fit by eye through the mean point, Pearson's r, and the regression line y = ax + b with its parameters interpreted.

SL 4.5Probability conceptsTrials and equally likely outcomes; P(A) = n(A)/n(U); complementary events; expected number of occurrences.

SL 4.6Combined eventsVenn, tree and sample-space diagrams; the addition rule; mutually exclusive, conditional and independent events.

SL 4.7Discrete random variablesProbability distributions and the expected value E(X) = Σxᵢ·P(X = xᵢ), applied to games and insurance-style contexts.

SL 4.8Binomial distributionNotation X ~ B(n, p) with mean np and variance np(1 − p); individual probabilities via the GDC.

SL 4.9Normal distributionProbabilities and inverse-normal calculations on the GDC, plus judging whether the model is reasonable for the data.

SL 4.10Spearman's rankWhen rank correlation is the better measure than Pearson's r, and how outliers affect each differently.

SL 4.11Hypothesis testingFormulating H₀ and H₁, significance levels and p-values; χ² tests for independence and goodness of fit; the t-test; one- and two-tailed decisions.

How it is examined

Hypothesis testing appears in SL Paper 2 exactly as it does beyond school statistics — as a procedure whose steps must all be visible.

Recent SL papers embed χ² tests and t-tests inside real scenarios — spending by weekend customers, crop yields — and award separate marks for hypotheses, p-value, and conclusion.
Conclusions must compare the p-value to the significance level and interpret the decision back into the scenario's language; 'reject H₀' alone is incomplete.
Regression questions check direction: predicting y requires the y-on-x line, a distinction examiners regularly penalise.
Distribution work (binomial, normal, inverse normal) is GDC-based but expects the setup — distribution chosen and parameters stated — before the output.
The booklet devotes five pages here — probability rules, expected value, binomial mean and variance — but no procedures at all: there is no normal formula and no χ² recipe to copy. The tests live in the GDC's statistics menu, so choosing which test to open is itself the examined skill.
Real papers also test sampling judgement in words — naming whether a plan was convenience, systematic or stratified sampling, then stating one disadvantage of it.

A marked question, mark by mark

A normal-distribution exercise with the contextual sentence that decides the final mark.

Rehearse the whole testing procedure, marked step by step

From SL 4.1 sampling to SL 4.11 t-tests, every generated exercise comes back with each mark awarded or withheld and a reason — including the contextual sentences students habitually omit.

Start free trial

New to the codes? M1, A1, R1 explained →

Normal distribution · SL 4.9

Seed 2E87

Battery lifetimes are modelled by a normal distribution with mean 120 hours and standard deviation 8 hours.

(a)Find the probability that a battery lasts fewer than 110 hours.
(b)Interpret this probability in context.

Your work

z = (110 − 120)/8 = −1.25

P(Z < −1.25) ≈ 0.106

Marks awarded

M1Mark awarded. Standardised correctly with μ = 120 and σ = 8 before applying technology.
A1Mark awarded. 0.106, correct to three significant figures.
R1Mark not awarded. No interpretation: the 0.106 was never linked to the proportion of batteries failing before 110 hours.

Where marks are actually lost

In this topic the calculator is rarely the problem — the surrounding language is.

Skipping the formal statement of H₀ and H₁ at the start of a test.

CostThe first marks of every hypothesis question are given away before any calculation happens.

Ending with 'reject H₀' instead of comparing the p-value to the significance level in a sentence about the scenario.

CostThe conclusion mark is explicitly reserved for the comparison and its meaning.

Predicting with the x-on-x line, or reading r ≈ ±1 as causation.

CostDirection of prediction and correlation-versus-causation are standing examiner penalties.

Trusting Pearson's r on clearly monotonic-but-nonlinear data where Spearman's rank is appropriate.

CostAppropriateness-of-measure judgements are marked, especially in the presence of outliers.