# How to evaluate AI

- Link: https://arqiv.si/ai/evaluating-ai/
- Published: 2026-10-10T14:16:20-04:00
- Author: Steven Ryan

[Skip to content](https://arqiv.si/ai/evaluating-ai/#main-content)

[arqiv](https://arqiv.si/)

[For educators](https://arqiv.si/teachers/)

Teach

 * [Start here](https://arqiv.si/teachers/)
 * [Lessons & printable kits](https://arqiv.si/teachers/resources/)
 * [Classroom labs](https://arqiv.si/teachers/labs/)
 * [Free 20-minute lesson](https://arqiv.si/teachers/free-ai-lesson/)

Plan

 * [Curriculum guide](https://arqiv.si/teachers/curriculum/)
 * [AI Learning Center](https://arqiv.si/teachers/ai-literacy/)
 * [Future of work unit](https://arqiv.si/future-of-work/)
 * [What the research says](https://arqiv.si/teachers/what-works/)
 * [AI education worldwide](https://arqiv.si/teachers/around-the-world/)

Understand

 * [Think First method](https://arqiv.si/teachers/think-first/)
 * [Our approach](https://arqiv.si/research/#our-method)
 * [AI vocabulary](https://arqiv.si/teachers/ai-vocabulary/)

By role

 * [Counselors](https://arqiv.si/counselors/)
 * [School leaders & PD](https://arqiv.si/schools/)
 * [Speaking & workshops](https://arqiv.si/speaking/)
 * [Products](https://arqiv.si/products/)

[Learn AI](https://arqiv.si/ai/topics/)

Start

 * [All AI topics](https://arqiv.si/ai/topics/)
 * [The AI journey, from zero](https://arqiv.si/ai/)
 * [Using AI well](https://arqiv.si/ai/talking-to-ai/)
 * [AI builds](https://arqiv.si/ai-builds/)

AI in the world

 * [Space](https://arqiv.si/space/)
 * [Weather](https://arqiv.si/weather/)
 * [Health](https://arqiv.si/health/)
 * [Engineering](https://arqiv.si/engineering/)
 * [Farming](https://arqiv.si/farming/)
 * [Quantum](https://arqiv.si/quantum/)

What it means

 * [Future of work](https://arqiv.si/future-of-work/)
 * [Your AI path](https://arqiv.si/ai/your-path/)
 * [Research, explained](https://arqiv.si/research/)

[Games & labs](https://arqiv.si/games/)[Research](https://arqiv.si/research/)[Blog](https://arqiv.si/blog/)
[About](https://arqiv.si/about/)

[Search or ask](https://arqiv.si/ai/topics/)[Newsletter](https://arqiv.si/newsletter/)
[ARQIV.FM ↗](https://arqiv.fm/)

Menu

For educators

[For educators: start page →](https://arqiv.si/teachers/)

Teach

 * [Start here](https://arqiv.si/teachers/)
 * [Lessons & printable kits](https://arqiv.si/teachers/resources/)
 * [Classroom labs](https://arqiv.si/teachers/labs/)
 * [Free 20-minute lesson](https://arqiv.si/teachers/free-ai-lesson/)

Plan

 * [Curriculum guide](https://arqiv.si/teachers/curriculum/)
 * [AI Learning Center](https://arqiv.si/teachers/ai-literacy/)
 * [Future of work unit](https://arqiv.si/future-of-work/)
 * [What the research says](https://arqiv.si/teachers/what-works/)
 * [AI education worldwide](https://arqiv.si/teachers/around-the-world/)

Understand

 * [Think First method](https://arqiv.si/teachers/think-first/)
 * [Our approach](https://arqiv.si/research/#our-method)
 * [AI vocabulary](https://arqiv.si/teachers/ai-vocabulary/)

By role

 * [Counselors](https://arqiv.si/counselors/)
 * [School leaders & PD](https://arqiv.si/schools/)
 * [Speaking & workshops](https://arqiv.si/speaking/)
 * [Products](https://arqiv.si/products/)

Learn AI

[Learn AI: start page →](https://arqiv.si/ai/topics/)

Start

 * [All AI topics](https://arqiv.si/ai/topics/)
 * [The AI journey, from zero](https://arqiv.si/ai/)
 * [Using AI well](https://arqiv.si/ai/talking-to-ai/)
 * [AI builds](https://arqiv.si/ai-builds/)

AI in the world

 * [Space](https://arqiv.si/space/)
 * [Weather](https://arqiv.si/weather/)
 * [Health](https://arqiv.si/health/)
 * [Engineering](https://arqiv.si/engineering/)
 * [Farming](https://arqiv.si/farming/)
 * [Quantum](https://arqiv.si/quantum/)

What it means

 * [Future of work](https://arqiv.si/future-of-work/)
 * [Your AI path](https://arqiv.si/ai/your-path/)
 * [Research, explained](https://arqiv.si/research/)

 * [Games & labs](https://arqiv.si/games/)
 * [Research](https://arqiv.si/research/)
 * [Blog](https://arqiv.si/blog/)
 * [About](https://arqiv.si/about/)

[Get the newsletter](https://arqiv.si/newsletter/)

 1.  [ARQIV / FOUNDATIONS](https://arqiv.si/ai/topics/)
 2.  [**01**Map of AI](https://arqiv.si/ai/map-of-ai/)
 3.  [**02**Machine learning](https://arqiv.si/ai/machine-learning/)
 4.  [**03**Data](https://arqiv.si/ai/data-and-datasets/)
 5.  [**04**Numbers & tensors](https://arqiv.si/ai/tensors/)
 6.  [**05**Training vs using](https://arqiv.si/ai/training-and-inference/)
 7.  [**06**Evaluating AI](https://arqiv.si/ai/evaluating-ai/)
 8.  [**07**Classical models](https://arqiv.si/ai/classical-machine-learning/)
 9.  [**08**Finding groups](https://arqiv.si/ai/unsupervised-learning/)
 10. [**09**Retrieval & RAG](https://arqiv.si/ai/retrieval-and-rag/)

AI foundations · 06

# Good at what, for whom, and _compared with what?_

A single score never proves that an AI system is good. You need to know which task
it was tested on, on whose data, which mistakes it made, and whether it beats a 
simple alternative. A model can be “90% accurate” and still be useless for the job
you have in mind.

Grades 7+20 minutesFractions and percentagesOptional: error and calibration

What you will be able to do

Calculate accuracy, precision and recall from a confusion matrix, compare a model
with a simple baseline, and explain why a high score can still fail a real use.

Before you start

Read [How can examples become a rule?](https://arqiv.si/ai/machine-learning/) (features,
labels, classification) and, if you can, [Training vs using](https://arqiv.si/ai/training-and-inference/).
You need to be comfortable with fractions.

1 · You have already seen this

## A score in a headline, _with nothing to compare it to_

You have probably seen an app or a news story say a model is “90% accurate.”

A number like that is easy to remember and hard to judge. Ninety percent of what,
tested how, and compared with what? When the thing a model looks for is rare, even
a model that never finds it can score high.

Working out whether a score means something is called **evaluating AI**. You ask
what task it was tested on, on whose data, which mistakes it made, and whether it
beats a simple alternative. The rest of this page shows how that works, lets you
try it, and shows where it goes wrong.

2 · What happens, step by step

## From a claim to _a fair test_

Testing a yes-or-no model in four steps. The next section goes deeper into steps
1 and 2, and the one after it into steps 3 and 4.

How a fair test works

### Four steps

 1. 1 · Pick a baselineChoose the simplest reasonable alternative, such as always guessing
    the most common answer. A score only means something next to it.
 2. 2 · Test on new examplesCheck the model on examples it never saw while learning.
    If test examples leak into training, the score is too good to be true.
 3. 3 · Count the outcomesSort every case into four boxes: caught, false alarm, missed
    and correct pass. That table is called a **confusion matrix**.
 4. 4 · Choose what mattersDecide which mistake costs more before you pick a number.
    A smoke alarm should rarely miss a fire, so it cares most about **recall**; a spam
    filter that hides real email cares most about **precision**.

Going deeper · steps 1 and 2

## A baseline and _examples it has never seen_

Two rules come before every metric. Without them, even a correct calculation can
tell you nothing.

**Compare with a baseline.** A baseline is the simplest reasonable alternative: 
always guess the most common answer, predict that tomorrow will be like today, or
use the rule people already follow. A score only means something next to it. If 
a weather model is right 80% of the time but “same as today” is right 78% of the
time, the model adds very little.

**Test on held-out data.** A model can memorize its training examples, so it is 
tested on examples it never saw while learning, usually with the three-way split
in the box. If test examples leak into training, the score is too good to be true.
[Data and datasets](https://arqiv.si/ai/data-and-datasets/) shows how leaks happen.

Then ask the three questions in the title. _Good at what?_ Name the task and the
metric. _For whom?_ Check the people, places and conditions where it will be used.
_Compared with what?_ Name the baseline.

Three-way split

### Who sees which data

 * **Training set**: the model learns from it.
 * **Validation set**: people use it to choose between versions and settings.
 * **Test set**: used once at the end, to estimate how the chosen model does on 
   new examples.

If you keep checking the test set and tweaking, it slowly turns into a validation
set and stops being a fair test.

Going deeper · steps 3 and 4

## Count the _four outcomes_

When a model answers yes or no, every case lands in one of four boxes. That table
is called a confusion matrix.

Predict first

A fictional sensor checks 100 cases and 10 of them are positive. A lazy “model” 
always answers _negative_. How accurate is it?

Show the answer

**90%.** It is right about all 90 negatives and wrong about all 10 positives. High
accuracy, zero usefulness. Keep that number in mind for the worked example.

Worked example

### One hundred made-up cases, one model

 1. The situationA fictional sensor checks 100 cases. In truth, **10 are positive**(
    the thing we want to find is there) and 90 are negative.
 2. What the model didIt **caught 8** positives (true positives), **missed 2** (false
    negatives), raised **9 false alarms** (false positives) and correctly passed **
    81** negatives (true negatives). Check: 8 + 2 + 9 + 81 = 100.
 3. AccuracyRight answers ÷ all cases = (8 + 81) ÷ 100 = 89%.
 4. PrecisionOf the 17 cases it flagged (8 + 9), how many were really positive? 8 ÷
    17 ≈ 47%. More than half of its alarms were false.
 5. RecallOf the 10 real positives, how many did it find? 8 ÷ 10 = 80%.
 6. The baselineA “model” that always says _negative_ is right 90 times out of 100:
    90% accuracy, higher than the real model. Its recall is 0 ÷ 10 = 0%. It never finds
    anything.

The numbers are invented for teaching. The lesson is real: when one answer is rare,
accuracy rewards ignoring it.

The confusion matrix for the worked example|  | Really positive (10) | Really negative (90) | Total | 
| Model says positive | 8 caught (true positives) | 9 false alarms (false positives) | 17 flagged | 
| Model says negative | 2 missed (false negatives) | 81 correct passes (true negatives) | 83 not flagged | 
| Total | 10 | 90 | 100 |

**Accuracy** divides by everything. **Precision** divides by what the model flagged:“
when it raises an alarm, how often is it real?” **Recall** divides by what was really
there: “of all the real cases, how many did it find?” Always say which denominator
you used.

Which number matters depends on which mistake costs more. A smoke alarm should rarely
miss a fire, so recall comes first and some false alarms are acceptable. A spam 
filter that hides real email annoys everyone, so its false alarms matter more and
precision comes first. Ask which errors matter _before_ choosing a metric, not after
you see which one looks best. (The **F1 score** combines precision and recall into
one number, but it still hides which mistake happened.)

3 · Try it

## Signal or _false alarm?_

Most classifiers give a score, and a person chooses the threshold that turns the
score into a yes or no.

Lab

### Where should the leaf checker draw the line?

A made-up greenhouse camera gives 20 leaves a leaf-spot score from 0 to 100. A gardener
then checked every leaf by hand. Move the threshold and watch the four outcomes,
the three metrics and the baseline change.

 Simulated in your browser with 20 made-up leaves. No real plants or real model.

Flag a leaf when its score is at least **50**

 leaf spot (found by the gardener) ·  healthy · Flagged leaves have a bright border.
Sorted from highest score to lowest.

Three challenges

 1. Find the highest threshold that still catches all 5 sick leaves. How many false
    alarms come with it?
 2. Find a threshold with the highest accuracy. What is the recall there? Would a gardener
    be happy?
 3. Set the threshold to 100. Compare the result with the baseline. What does that 
    tell you about accuracy?

The 20 made-up leaves, from highest score to lowest, with what the gardener found:
94 (spot), 83 (spot), 78 (healthy), 71 (spot), 66 (healthy), 57 (spot), 52 (healthy),
45 (healthy), 41 (healthy), 36 (spot), 33 (healthy), 28 (healthy), 24 (healthy),
19 (healthy), 15 (healthy), 12 (healthy), 9 (healthy), 7 (healthy), 4 (healthy),
2 (healthy).

A leaf is flagged when its score is at least the threshold. Here is what six thresholds
do. The “always say healthy” baseline gets 15/20 = 75% accuracy and catches 0 of
5 sick leaves.

Signal or false alarm: six thresholds| Threshold | Caught | False alarms | Missed | Correct passes | Accuracy | Precision | Recall | 
| 0 | 5 | 15 | 0 | 0 | 5/20 = 25% | 5/20 = 25% | 5/5 = 100% | 
| 35 | 5 | 5 | 0 | 10 | 15/20 = 75% | 5/10 = 50% | 5/5 = 100% | 
| 50 | 4 | 3 | 1 | 12 | 16/20 = 80% | 4/7 = 57% | 4/5 = 80% | 
| 55 | 4 | 2 | 1 | 13 | 17/20 = 85% | 4/6 = 67% | 4/5 = 80% | 
| 80 | 2 | 0 | 3 | 15 | 17/20 = 85% | 2/2 = 100% | 2/5 = 40% | 
| 100 | 0 | 0 | 5 | 15 | 15/20 = 75% | nothing flagged | 0/5 = 0% |

**Same idea, different stakes.** The ARQIV [health threshold lab](https://arqiv.si/health/#lab)
uses this trade-off for screening. When the scores overlap, no line removes every
mistake; moving it trades misses for false alarms. Choosing where to put it is a
decision about costs, and people, not the model, should make it.

Predicting numbers

## How far off, _on average?_

When the output is a number, such as a temperature, there is no “right or wrong,”
only how far off.

For a numeric prediction, the error is the distance between the prediction and what
really happened. The **mean absolute error** (MAE) averages those distances, ignoring
whether the guess was too high or too low. It is in the same units as the prediction,
so “MAE 1 °C” is easy to picture.

The made-up forecast in the table has an MAE of 1.0 °C. Is that good? Compare it
with the baseline “tomorrow will be like today,” which has an MAE of 1.75 °C on 
the same days. Weather forecasters compare against baselines like this one; see 
[AI in weather](https://arqiv.si/weather/). A cousin of MAE, RMSE, punishes big 
misses more strongly.

Made-up temperatures (Sunday was 18 °C)| Day | Actual | Model | Model error | “Same as today” | Baseline error | 
| Mon | 17 °C | 18 °C | 1 | 18 °C | 1 | 
| Tue | 20 °C | 22 °C | 2 | 17 °C | 3 | 
| Wed | 19 °C | 19 °C | 0 | 20 °C | 1 | 
| Thu | 21 °C | 20 °C | 1 | 19 °C | 2 | 
| MAE |  |  | 4 ÷ 4 = **1.0** |  | 7 ÷ 4 = **1.75** |

Beyond the average

## For whom, how sure, _and for how long?_

A model can pass every test on average and still fail a particular group, a particular
confidence level or a new season.

Subgroup checks

### Fine on average, poor for some

A made-up leaf checker finds 40 of 50 sick leaves: 80% recall. Split by greenhouse,
it finds 36 of 40 in the sunny one (90%) but only 4 of 10 in the shady one (40%).
The average hid the problem because the shady greenhouse had fewer leaves. Always
break results down by the groups that matter, especially groups of people.

Calibration

### When it says 80%, is it right 80% of the time?

Many models output a confidence. A **calibrated** model that says “80% likely” is
right about 80% of the time it says so. If 50 leaves each got “80%” and only 28 
really had leaf spot (56%), the model is overconfident. A score like the one in 
the lab is not a probability unless someone has checked it this way.

Distribution shift

### The world changes after the test

A model tested on summer photos from one camera may do worse with winter light or
a new camera. When the data in use drifts away from the data it was tested on, old
scores stop applying, so systems in use need checking again. The [farming weed spotter](https://arqiv.si/farming/)
asks the same question: what changes with lighting?

Chatbots and generators

## When there is no _single right answer_

A chatbot’s answer, a summary or an image cannot be checked against one label, so
evaluation becomes a set of separate checks.

Separate panel · generative systems

### Five checks instead of one score

Five things to measure in a generative system| What to check | An example test | Watch out for | 
| Factual support | For 30 answers, does every claim match a source you can open? | Fluent, confident text with no support (hallucination) | 
| Task success | Did the summary keep the five key points? Does the code pass its tests? | Judging by how good it sounds instead of what it did | 
| Safety failures | How often does it give harmful help, or refuse a harmless request? | Testing only polite, easy prompts | 
| Latency and cost | Seconds per answer, and price per 1,000 answers | A small quality gain that costs ten times more | 
| Consistency | Ask the same question five times: do the answers agree? | Showing your best run instead of a typical one |

**Benchmarks** are shared test sets that let people compare models, but a high benchmark
score is not your task: the questions may differ from yours, and test questions 
can leak into training data. Run a small, fair test on your own task, with the same
prompts for every model. [Test the models](https://arqiv.si/teachers/test-the-models/)
shows how to do this with a class.

**An AI judge gives you evidence, and it can be wrong.** It is common to ask one
language model to grade another’s answers. This is fast and often agrees with people,
but judges have known biases: they can prefer longer answers, the answer shown first,
or answers written in their own style, and they can miss the same false facts. Check
a sample of judgments yourself, and verify claims with sources, as in the [Verify lab](https://arqiv.si/teachers/verify-lab/).

4 · Common mix-ups

## A high score can _still mislead_

Four ideas that trip people up, and what to think instead.

 * **Mix-up:** High accuracy means a good model.
 * **Better:** Accuracy can be high just because one answer is rare. Compare it 
   with the “always the common answer” baseline and look at precision and recall.
 * **Mix-up:** Precision and recall are two names for the same thing.
 * **Better:** They divide by different groups: precision by everything the model
   flagged, recall by everything that was really there.
 * **Mix-up:** A score of 0.8 means an 80% chance.
 * **Better:** Only if the model is calibrated. Many scores are just rankings.
 * **Mix-up:** If an AI judge gave it 9 out of 10, it is good.
 * **Better:** An AI judge is one more model with its own biases. Treat its grades
   as evidence to check.

5 · Check yourself

## Three _quick questions_

Answer in your head or on paper before you open each one.

 1.  In the worked example, the model scores 89% accuracy and “always negative” scores
     90%. Why does accuracy alone mislead here?
 2.  Check your answer
 3.  Because only 10 of 100 cases are positive, ignoring them all still gives 90% accuracy.
     Accuracy does not show that the baseline finds 0 of 10 positives while the model
     finds 8 of 10 (80% recall). You need recall and precision, and a decision about
     which mistakes matter.
 4.  A fictional fruit sorter flags 20 apples as bruised. 15 of them really are bruised,
     and 10 bruised apples were not flagged. What are its precision and recall?
 5.  Check your answer
 6.  Precision = 15 ÷ 20 = **75%** (of the flagged apples, three quarters were bruised).
     Recall = 15 ÷ (15 + 10) = 15 ÷ 25 = **60%** (of the 25 bruised apples, it found
     15). Same 15 on top, different denominators.
 7.  A school tests a homework chatbot on 50 questions and an AI judge scores it 92%.
     Name two more things you would check before trusting it.
 8.  Check your answer
 9.  Good answers include: check a sample of the judge’s grades yourself; compare with
     a baseline (another tool, or a textbook); check factual claims against sources;
     test on questions from the subjects and grade levels your students actually have;
     check for harmful or wrong answers; and see whether the score holds on new questions
     it could not have seen.

For younger learners

## A _grades 4–6_ version

No percentages needed: just counting four kinds of outcomes.

20 minutes · teacher-led

### The ripe-fruit helper

 1. Make 12 picture cards of fruit; 3 are ripe.
 2. A pretend “helper” (the teacher) calls each card ripe or not ripe, making a few
    deliberate mistakes.
 3. Students sort the cards into four piles: caught, false alarm, missed, correct pass.
 4. Ask: a helper that always says “not ripe” is right 9 times out of 12. Is it a good
    helper?

Exit question

### Which mistake is worse?

For a fruit picker, is it worse to miss a ripe fruit or to pick an unripe one? Good
answers give a reason, and notice that the answer changes with the job.

Honest limits

## What this page _leaves out_

What this page leaves out

Many metrics get no space here: F1 in detail, ROC curves and AUC, RMSE, ranking 
metrics, and fairness metrics that compare error rates between groups. Real evaluations
also need enough test cases: with 20 leaves, one leaf moves accuracy by 5 points.
Measuring a system in use (monitoring) is a topic of its own.

Where to go next

## Use these _questions everywhere_

Next stop · 07

### Do you always need a neural network?

Compare five simple models on one tiny dataset, using training and test accuracy.

For the classroom

### Test the models

Run a fair, small test of chatbots on your own questions.

Thresholds at work

### Where should the AI draw the line?

The same trade-off between misses and false alarms, in screening.

Evaluating AI apps

### AI in production

LLM-as-a-judge, RAGAS, agent evals and regression tests that run before every change.

Sources

## Where this comes from

 1. [Google for Developers, Machine Learning Crash Course: “Classification: Accuracy, recall, precision, and related metrics.”](https://developers.google.com/machine-learning/crash-course/classification/accuracy-precision-recall)
 2. [Google for Developers, Machine Learning Crash Course: “Dividing the original dataset” (training, validation and test sets).](https://developers.google.com/machine-learning/crash-course/overfitting/dividing-datasets)
 3. [scikit-learn User Guide, “Metrics and scoring”: definitions of accuracy, precision, recall, F1, mean absolute error and more.](https://scikit-learn.org/stable/modules/model_evaluation.html)
 4. [scikit-learn User Guide, “Probability calibration”: what it means for predicted probabilities to match observed frequencies.](https://scikit-learn.org/stable/modules/calibration.html)
 5. [Lianmin Zheng et al. (2023), “Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena”: LLM judges often agree with people but show position, length and self-preference biases.](https://arxiv.org/abs/2306.05685)
 6. [NIST, AI Risk Management Framework: measuring and monitoring AI systems in context, beyond a single test score.](https://www.nist.gov/itl/ai-risk-management-framework)

AI words on this page

[Evaluation](https://arqiv.si/teachers/ai-vocabulary/#evaluation), [Baseline](https://arqiv.si/teachers/ai-vocabulary/#baseline),
[Test set](https://arqiv.si/teachers/ai-vocabulary/#test-set), [Validation set](https://arqiv.si/teachers/ai-vocabulary/#validation-set),
[Confusion matrix](https://arqiv.si/teachers/ai-vocabulary/#confusion-matrix), [Precision and recall](https://arqiv.si/teachers/ai-vocabulary/#precision-and-recall),
[False positive](https://arqiv.si/teachers/ai-vocabulary/#false-positive), [F1 score](https://arqiv.si/teachers/ai-vocabulary/#f1-score),
[Base rate](https://arqiv.si/teachers/ai-vocabulary/#base-rate), [Calibration](https://arqiv.si/teachers/ai-vocabulary/#calibration),
[Distribution shift](https://arqiv.si/teachers/ai-vocabulary/#distribution-shift),
[Data leakage](https://arqiv.si/teachers/ai-vocabulary/#data-leakage), [Benchmark](https://arqiv.si/teachers/ai-vocabulary/#benchmark),
[Hallucination](https://arqiv.si/teachers/ai-vocabulary/#hallucination)

All definitions live in one place: [AI words in plain language →](https://arqiv.si/teachers/ai-vocabulary/)

Review status

Written by ARQIV. Last checked October 2026. Independent subject review and classroom
pilots are still to come, so treat the activities as drafts and [tell us](https://arqiv.si/ai/evaluating-ai/info@arqiv.fm?subject=AI%20foundations%20correction)
about anything that is wrong or unclear.

[← Previous**Training vs using**](https://arqiv.si/ai/training-and-inference/)[Next →**Classical models**](https://arqiv.si/ai/classical-machine-learning/)

[arqiv](https://arqiv.si/)

A little understanding changes everything.

[LISTEN: ARQIV.FM, OUR WEEKLY SHOW ↗](https://arqiv.fm/)

Educators

 * [Start here](https://arqiv.si/teachers/)
 * [Lessons & kits](https://arqiv.si/teachers/resources/)
 * [Curriculum](https://arqiv.si/teachers/curriculum/)
 * [Labs](https://arqiv.si/teachers/labs/)
 * [AI vocabulary](https://arqiv.si/teachers/ai-vocabulary/)

For your role

 * [Counselors](https://arqiv.si/counselors/)
 * [School leaders & PD](https://arqiv.si/schools/)
 * [Speaking & workshops](https://arqiv.si/speaking/)
 * [Products](https://arqiv.si/products/)

Learn

 * [Learn AI](https://arqiv.si/ai/topics/)
 * [Games & labs](https://arqiv.si/games/)
 * [Future of work](https://arqiv.si/future-of-work/)
 * [Research](https://arqiv.si/research/)
 * [Headlines](https://arqiv.si/news/)

ARQIV

 * [About & corrections](https://arqiv.si/about/)
 * [Our approach](https://arqiv.si/research/#our-method)
 * [Newsletter](https://arqiv.si/newsletter/)
 * [Privacy](https://arqiv.si/privacy-policy/)
 * [Get in touch](https://arqiv.si/ai/evaluating-ai/info@arqiv.fm)

Classroom activities collect no student data.[info@arqiv.fm](https://arqiv.si/ai/evaluating-ai/info@arqiv.fm)
