CBSE Class 10 · Artificial Intelligence · board exam 2027
CBSE Class 10 Artificial Intelligence Question Paper 2026
The board’s 2026 question paper, set 115 — all 46 questions as printed; 27 objective answers from the board’s own key; full model answers for 3 written questions, how the answer begins for 16 more. Each question names its chapter, where that chapter’s most-asked questions are.
Full marks 50 · Time 2 h
Section A · Written questions (30)
Identify the imperative sentence :
- (A) Shut the front door. ✓
- (B) She is talented artist.
- (C) Are you feeling better ?
- (D) You were amazing !
Answer (the board’s key): (A)
Breaking down big goals into smaller parts will make the goal _________.
- (A) specific
- (B) measurable
- (C) achievable ✓
- (D) realistic
Answer (the board’s key): (C)
Define the term ‘Time Management’.
Medha Ma’am
Ask Medha’s AI teacher
Model answer · definition, time management
- 1.Time management is the ability to plan and control how you spend the hours of your day well and do all that you want to do, so as to increase efficiency and productivity.1 mark
- Begin the answer with the words 'Time management is the ability to plan and control'.
- Mention that it helps to increase efficiency and productivity of the day's activities.
Marks split from a structure derived from past papers (checked twice); not CBSE’s official scheme
What should a strong password consist of ?
- (A) Only letters
- (B) Numbers and special characters
- (C) Name of a person
- (D) Letters, numbers and special characters ✓
Answer (the board’s key): (D)
A misconception about an entrepreneur is : Entrepreneurs are ___________, not __________.
Medha Ma’am
Ask Medha’s AI teacher
Model answer · Misconceptions about entrepreneurship
- 1.Entrepreneurs are born, not made. This is a misconception, which means a false belief. In truth, an entrepreneur is a person who does whatever it takes to make the business successful. Being an entrepreneur starts with a way of thinking, so anyone can become one.1 mark
- Fill the blanks in the right order: "born" goes in the first blank and "made" in the second.
- Write the full sentence "Entrepreneurs are born, not made" so both words are seen together.
Marks split from a structure derived from past papers (checked twice); not CBSE’s official scheme
Choose the option which is NOT a Sustainable Development Goal according to United Nations.
- (A) Population ✓
- (B) No poverty
- (C) Quality education
- (D) Reduced Inequalities
Answer (the board’s key): (A)
Anita and Surjit are creating an AI application that will classify different types of fruits. The Computer Vision task that will identify the type of fruit and assign a label to it is called ________.
- (A) Segmentation
- (B) Classification ✓
- (C) Classification + Localization
- (D) Object Detection
Answer (the board’s key): (B)
Consider the following sentence: On seeing her son's result, Pooja's face turned red with anger. Which feature of natural language does the word "red" represent?
- (A) Redundancy
- (B) Context-dependent meaning ✓
- (C) Grammatical structure
- (D) Temporal change
Answer (the board’s key): (B)
Ethical frameworks are primarily designed for what?
- (A) Increasing the functionality of AI algorithms.
- (B) Ensuring that the decisions made do not cause any unintended harm. ✓
- (C) Reducing the cost of AI development.
- (D) Speeding up the AI project cycle.
Answer (the board’s key): (B)
Statement 1: Overfitting occurs when a model memorizes the training data instead of learning patterns. Statement 2: Using the same data for training and evaluation helps the model give correct results.
- (A) Both statements are correct.
- (B) Both statements are incorrect.
- (C) Statement 1 is correct, but Statement 2 is incorrect. ✓
- (D) Statement 1 is incorrect, but Statement 2 is correct.
Answer (the board’s key): (C)
Which learning approach would be most suitable for training an AI model to park a car correctly?
- (A) Supervised Learning
- (B) Unsupervised Learning
- (C) Transfer Learning
- (D) Reinforcement Learning ✓
Answer (the board’s key): (D)
Which stage of the AI Project Cycle involves testing the model on newly fetched data ?
- (A) Data Exploration
- (B) Modelling
- (C) Evaluation ✓
- (D) Deployment
Answer (the board’s key): (C)
In the context of autonomous vehicle safety systems, which type of error would be most critical to minimize ?
- (A) False Positive (detecting danger when there isn't any)
- (B) False Negative (failing to detect actual danger) ✓
- (C) True Positive (detecting danger correctly)
- (D) True Negative (correctly identifying that there is no danger)
Answer (the board’s key): (B)
What is the range of possible pixel values in a byte image format ?
- (A) 0 to 100
- (B) 0 to 255 ✓
- (C) 1 to 256
- (D) -128 to 127
Answer (the board’s key): (B)
An e-commerce platform analyzes customer purchase patterns to recommend “Customers who bought product x also bought product y.” This uses :
- (A) Classification model
- (B) Regression model
- (C) Association model ✓
- (D) Clustering model
Answer (the board’s key): (C)
Since AI is actually being used as a tool for decision making/influencing, we need to ensure that AI makes ethically acceptable recommendations. Which of the following is a key factor that can knowingly or unknowingly influence our decision making while designing an AI model ?
- (A) Intuition and values ✓
- (B) Algorithm efficiency
- (C) Data storage capacity
- (D) Processing speed
Answer (the board’s key): (A)
Which NLP application is helpful in converting natural speech to text in real time ?
- (A) Keyword Extraction tool
- (B) Translation of books from English to Hindi language
- (C) Auto generated captions on YouTube ✓
- (D) Classifying raw text into pre-defined groups
Answer (the board’s key): (C)
In Supervised learning, what is the purpose of the testing dataset ?
- (A) To train the model.
- (B) To evaluate the accuracy of the model. ✓
- (C) To create new features.
- (D) To label the data.
Answer (the board’s key): (B)
In a fire alarm system, if the model predicts “Fire Present” when there is actually no fire, this is classified as :
- (A) True Positive (TP)
- (B) True Negative (TN)
- (C) False Positive (FP) ✓
- (D) False Negative (FN)
Answer (the board’s key): (C)
Assertion (A): Bioethics is an example of a value-based framework for AI. Reason (R): Bioethics deals with ethical issues related to health, medicine and biology.
- (A) Both (A) and (R) are true and (R) is the correct explanation of (A).
- (B) Both (A) and (R) are true, but (R) is not the correct explanation of (A).
- (C) (A) is true, but (R) is false.
- (D) (A) is false, but (R) is true. ✓
Answer (the board’s key): (D)
Which scenario best represents a regression problem?
- (A) Identifying whether an email is spam.
- (B) Grouping customers according to behaviour.
- (C) Predicting tomorrow's temperature. ✓
- (D) Recognising faces in a photo.
Answer (the board’s key): (C)
Which of the following best describes the relationship between pixels and image resolution?
- (A) Having more pixels reduces the image quality.
- (B) Pixels and resolution are not related concepts.
- (C) Resolution depends only on the size of the image file.
- (D) The number of pixels in an image is known as resolution. ✓
Answer (the board’s key): (D)
Precision is defined as :
- (A) ratio of correctly predicted positive observation and total observation
- (B) ratio of correctly predicted positive observation and total predicted positive observation ✓
- (C) ratio of correctly predicted negative observation and total observation
- (D) harmonic mean of true positive and true negative
Answer (the board’s key): (B)
Which type of chat bot requires coding and works on bigger databases directly ?
- (A) Script bot
- (B) Smart bot ✓
- (C) Traditional bot
- (D) Rule-based bot
Answer (the board’s key): (B)
Which AI domain would be most suitable for developing a price comparison website ?
- (A) Computer Vision
- (B) Natural Language Processing
- (C) Statistical Data ✓
- (D) Robotics
Answer (the board’s key): (C)
Assertion (A) : Converting text to lowercase is preferable in text preprocessing. Reason (R) : It ensures that “Hello” and “hello” are treated as the same word by the machine.
- (A) Both (A) and (R) are true and (R) is the correct explanation of ✓
- (B) Both (A) and (R) are true, but (R) is not the correct explanation of (A).
- (C) (A) is true, but (R) is false.
- (D) (A) is false, but (R) is true.
Answer (the board’s key): (A)
In the context of Computer Vision vs Image Processing, which statement correctly differentiates them ?
- (A) Computer Vision and Image Processing are exactly the same.
- (B) Computer Vision enhances the image while Image Processing does not.
- (C) Computer Vision is a superset of Image Processing. ✓
- (D) Image Processing is a superset of Computer Vision.
Answer (the board’s key): (C)
State True or False : In machine learning, the error is used to see how accurately the model can predict data.
Medha Ma’am
Ask Medha’s AI teacher
Model answer · accuracy and error, model evaluation
- 1.True. In Machine Learning, the error is used to see how accurately our model can predict data it uses to learn new, unseen data.1 mark
- Start the answer with the word True.
- Write that error is used to see how accurately the model can predict data, using these exact words.
Marks split from a structure derived from past papers (checked twice); not CBSE’s official scheme
A company wants to analyze customer reviews to understand satisfaction levels. Which NLP application would be most suitable ?
- (A) Text classification
- (B) Sentiment analysis ✓
- (C) Keyword extraction
- (D) Language translation
Answer (the board’s key): (B)
An AI model was tested with 1000 test samples. If True Positive (TP) = 200, True Negative (TN) = 600, False Positive (FP) = 100, False Negative (FN) = 100, how many total predictions were correct ?
- (A) 300
- (B) 600
- (C) 800 ✓
- (D) 900
Answer (the board’s key): (C)
Section B · Written questions (16)
Write the 7 C's of communication.
How the model answer begins
1. The basic principles of professional communication skills can be abbreviated as 7 Cs i.e., Clear, Concise, Concrete, Correct, Coherent, Complete and Courteous.
The full answer from Medha Ma’am →(a) What is emotional intelligence ? (b) Name any two skills included in emotional intelligence.
How the model answer begins
1. (a) Emotional intelligence is the ability to identify and manage one's own emotions, as well as the emotions of others.
The full answer from Medha Ma’am →How ICT skills help us in our day-to-day activities ?
How the model answer begins
1. ICT skills help us in searching and processing information quickly. This helps us in our day-to-day activities to find and use the information we need without delay.
The full answer from Medha Ma’am →State the qualities to become a successful entrepreneur.
How the model answer begins
1. A successful entrepreneur must possess the ability to take risks. A self-employed person who is always trying to make his/her business better by taking risks and trying new ideas is an entrepreneur. He/she must also be…
The full answer from Medha Ma’am →Define the term 'Sustainable Development'
How the model answer begins
1. Sustainable development is the development that satisfies the needs of the present without compromising the capacity of future generations, guaranteeing the balance between economic growth, care for the environment and…
The full answer from Medha Ma’am →Explain the difference between sector-based and value-based ethical frameworks with one example of each.
How the model answer begins
1. A sector-based ethical framework is a framework tailored to specific sectors or industries, that is, a set of rules and standards created for specific industries or professions such as finance, education,…
The full answer from Medha Ma’am →Give any two characteristics of a Classification Model.
How the model answer begins
1. A Classification model uses predefined classes in which objects are assigned, that is, the data is classified according to the labels to categorize data into predefined categories or classes. For example, in the grading…
The full answer from Medha Ma’am →How do computers store RGB images ?
How the model answer begins
1. All the coloured images that we see around us are made up of three primary colours Red, Green, and Blue. All the colours that are present can be made by combining different intensities of red, green, and blue.
The full answer from Medha Ma’am →Give two differences between Supervised and Unsupervised learning.
How the model answer begins
1. Supervised learning uses labelled data, whereas unsupervised learning uses unlabelled data.
The full answer from Medha Ma’am →Explain Train-test split technique with respect to machine learning algorithm.
How the model answer begins
1. The train-test split is a technique for evaluating the performance of a machine learning algorithm.
The full answer from Medha Ma’am →How is Stemming different from Lemmatization ? Explain how the word "Wolves" would be processed by stemming and lemmatization.
How the model answer begins
1. Stemming and lemmatization both remove the affixes of words. Stemming: the stemmed word may not be meaningful, because it only removes the affixes, so it is faster. Lemmatization: the word we get after affix removal…
The full answer from Medha Ma’am →Differentiate between Deep Learning, Artificial Intelligence and Machine Learning. Also draw a labelled Venn diagram depicting the relationship between AI, ML and DL.
How the model answer begins
1. Artificial Intelligence is a broad field that enables machines to perform tasks like human intelligence. It becomes intelligent according to the training it gets, and for this training, the machine is fed with datasets…
The full answer from Medha Ma’am →Consider the following scenarios and identify which AI domain would be most appropriate for each, with justification : (A) An AI based education platform needs to translate to English language and analyze thousands of student essays to provide instant feedback on grammar, content quality and writing style. (B) An AI based application installed on a busy crossing in a metropolitan city scans all vehicles driving through that crossing during peak traffic hours and categorizes them into four wheelers and two wheelers.
How the model answer begins
1. The most suitable AI domain for scenario (A) is Natural Language Processing (NLP). Natural Language Processing is a branch of artificial intelligence that deals with the interaction between computers and humans using…
The full answer from Medha Ma’am →Read the following paragraph and answer the questions that follow : PQR Security Solutions has designed an AI Model to detect cyber attacks on E-Commerce websites. For this, various network activities were monitored and analyzed on one of the websites. The model was tested on a dataset of 1500 network activities. Out of these, the model correctly predicted that 1000 were cyber attacks. It also correctly identified that 250 were not cyber attacks. However, the model predicted that 200 were cyber attacks but actually they were not. Additionally, it predicted that 50 were not cyber attacks but they actually were. (A) Draw the confusion matrix based on the given scenario. (B) How many total cases are True Negative in the above scenario ? (C) Calculate Precision.
How the model answer begins
1. In the given scenario, the model correctly predicted that 1000 were cyber attacks, which is the True Positive (TP) value. It correctly identified that 250 were not cyber attacks, which is the True Negative (TN) value.…
The full answer from Medha Ma’am →(A) Write the full form of CNN and ANN and define them. (B) In the given diagram of a Neural network, identify the layer that should be shown in Box 1 and Box 2 :
How the model answer begins
1. The full form of CNN is 'Convolutional Neural Network'. Convolutional Neural Network is a Deep Learning algorithm which can take in an input image, assign importance (learnable weights and biases) to various…
The full answer from Medha Ma’am →Consider the following documents : Document 1 : Data Science requires information. Document 2 : Information analysis requires data. Implement all the four steps of Bag of Words (BoW) model to create a document vector table.
How the model answer begins
1. Step 1 – Text normalisation (lowercase, punctuation removed): Document 1 → [data, science, requires, information]; Document 2 → [information, analysis, requires, data].
The full answer from Medha Ma’am →
The same preparation, with Medha Ma’am — on your phone
Every question of every chapter with its model answer, practice questions in the board’s own shapes, 45 minutes of class a day, written answers marked, a test every Sunday and a WhatsApp report to parents.
Medha Ma’am is an AI teacher, not a live tutor. Every answer is checked twice; a person takes responsibility.