CBSE Class 12 Sample Paper 2026 Solution for Artificial Intelligence

CBSE BOARD

SAMPLE
PAPER
2026

DOWNLOAD

CBSE | DEPARTMENT OF SKILL EDUCATION
ARTIFICIAL INTELLIGENCE (SUBJECT CODE - 843)
MARKING SCHEME FOR CLASS XII (SESSION 2025-2026)
Max. Time: 2 Hours Max. Marks: 50
General Instructions:
1. Please read the instructions carefully.
2. This Question Paper consists of 21 questions in two sections – Section A & Section B.
3. Section A has Objective type questions whereas Section B contains Subjective type questions.
4. Out of the given (5 + 16 =) 21 questions, a candidate has to answer (5 + 10 =) 15 questions in the
allotted (maximum) time of 2 hours.
5. All questions of a particular section must be attempted in the correct order.
6. SECTION A - OBJECTIVE TYPE QUESTIONS (24 MARKS):
i. This section has 05 questions.
ii. There is no negative marking.
iii. Do as per the instructions given.
iv. Marks allotted are mentioned against each question/part.
7. SECTION B – SUBJECTIVE TYPE QUESTIONS (26 MARKS):
i. This section contains 16 questions.
ii. A candidate has to do 10 questions.
iii. Do as per the instructions given.
iv. Marks allotted are mentioned against each question/part.

SECTION A: OBJECTIVE TYPE QUESTIONS
Source
Material Unit
Page no.
Q. (NCERT/PS /
QUESTION of source Marks
No. SCIVE/ Chap
CBSE Study . No.
Material)
Q. 1 Answer any 4 out of the given 6 questions on Employability Skills (1 x 4 = 4 marks)
d) Wait until Priya finishes speaking, then respond to her
i. NCERT 1 6 1
points.
ii. Neuroticism NCERT 2 34 1

iii. a) 1 → b, 2 → c, 3 → a NCERT 2 23 1
a) The arrangement of content (text, images, shapes)
iv. NCERT 3 76 1
changes
a) Both A and R are correct, and R is the correct
v. NCERT 4 79,80 1
explanation of A
117,
vi. True NCERT 5 1
118

Page 1 of 8

Q. 2 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
i. b) 1 → d, 2 → c, 3 → b, 4 → a Study 2 19 – 27 1
ii. Machine Vision Study 3 44 1
iii. d) Moore's Law Study 5 93 1
iv. Deep Neural Network Study 6 105 1
v. 1 → user prompt; 2 → training data Study 7 129 1
vi. c) Insight Study 8 151 1

Q. 3 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
i. Feature Engineering Study 2 26 1
ii. d) False Negative, False Positive Study 2 35 1
c) 1 → b, 2 → a, 3 → c, 4 → d
iii. Study 3 50,51 1
iv. a) Printed Library catalogue data Study 5 87 1
v. d) Linear Regression Study 6 105 1
vi. Change Study 8 153 1

Q. 4 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
a) Both A and R are correct, and R is the correct
i. Study 2 29 1
explanation of A.
ii. Pixels Study 3 45 1

Page 2 of 8

iii. b) Quantum Computing Study 5 99 1
iv. b) Learning rule Study 6 106 1
Generator, Discriminator.
v. Study 6 111 1
(½ mark for each correct answer)
127,
vi. c) 1 → d, 2 → b, 3 → c, 4 → a Study 7 1
128

Q. 5 Answer any 5 out of the given 6 questions (1 x 5 = 5 marks)
i. True Study 2 30 1
a) Both A and R are correct, and R is the correct
ii. Study 3 49 1
explanation of A.
iii. b) Object Detection Study 3 52 1
110,
iv. b) 1 → a, 2 → b, 3 → c Study 6 1
111
v. Latent space Study 7 125 1
vi. d) Candle stick chart Study 8 156 1

SECTION B: SUBJECTIVE TYPE QUESTIONS
Source
Material Unit
Page no.
Q. (NCERT/ /
QUESTION of source Marks
No. PSSCIVE/ Chap
CBSE Study . No.
Material)
Answer any 3 out of the given 5 questions on Employability Skills in 20 – 30 words each
(2 x 3 = 6 marks)
The words — “Wow!”, “Oh no!”, “Thanks!”, “Help!” —
are known as interjections.
They are words that express strong emotions, such as
Q. 6 NCERT 1 13 2
happiness, surprise, anger or pain.
(1 mark for identifying the word interjection; 1 mark for
explanation)

Page 3 of 8

• Talk to someone. Most often, it helps to share your
feelings.
• Look after your physical health. A healthy body can
help you maintain a healthy mind.
• Build confidence in your ability to handle difficult
Q. 7 situations. NCERT 2 37 2
• Engage in hobbies, such as music, dance and painting.
These have a therapeutic effect.
• Stay positive by choosing words like ‘challenges’
instead of ‘problems’.
(any 2 points; 1 mark per point)
a) Alignment feature.
b) Default Positioning:
• Text is left-aligned by default.
54,
Q. 8 • Numbers are right-aligned by default. NCERT 3 2
57
(1 mark for identifying the term alignment; ½ mark each
for correctly stating the default text alignment and
number alignment.)
a) Taking initiative
101,
Q. 9 b) Perseverance NCERT 4 2
103
(1 mark each)
Waste exchange is when the waste product of one
process becomes the raw material for another.
It helps in reducing waste disposal by reusing waste,
Q. 10 thereby minimizing the amount sent to landfills. NCERT 5 120 2
(1 mark for explaining the meaning of waste exchange.
1 mark for explaining how it helps in reducing waste
disposal.)
Answer any 4 out of the given 6 questions in 20 – 30 words each (2 x 4 = 8 marks)
Data Science Methodology is a process with a prescribed
sequence of iterative steps that data scientists follow to
approach a problem and find a solution.
It consists of ten steps.
Q. 11 Study 2 18 2
(prescribed sequence of iterative steps – ½ mark
data scientists follow – ½ mark
approach a problem and find a solution – ½ mark
10 steps – ½ mark)
1. Reasoning and Analytical Issues: Computer vision
relies on more than just image identification; it
requires accurate interpretation. Robust reasoning
and analytical skills are essential for defining attributes
within visual content. Without such capabilities,
extracting meaningful insights from images becomes CBSE
Q. 12 challenging, limiting the effectiveness of computer Study 3 55 2
vision systems. material
2. Difficulty in Image Acquisition: Image acquisition in
computer vision is hindered by various factors like
lighting variations, perspectives, and scales.
Understanding complex scenes with multiple objects
and handling occlusions adds to the complexity.
Page 4 of 8

Obtaining high-quality image data amidst these
challenges is crucial for accurate analysis and
interpretation.
3. Privacy and Security Concerns: Vision-powered
surveillance systems raise serious privacy concerns,
potentially infringing upon individuals' privacy rights.
Technologies like facial recognition and detection
prompt ethical dilemmas regarding privacy and
security. Regulatory scrutiny and public debate
surround the use of such technologies, necessitating
careful consideration of privacy implications.
4. Duplicate and False Content: Computer vision
introduces challenges related to the proliferation of
duplicate and false content. Malicious actors can
exploit vulnerabilities in image and video processing
algorithms to create misleading or fraudulent content.
Data breaches pose a significant threat, leading to the
dissemination of duplicate images and videos,
fostering misinformation and reputational damage.
(any 2 points; ½ mark for each challenge; ½ mark for its
relevant explanation)

Batch Processing Stream Processing
Processes large volumes Processes continuous
of data all at once within streams of data
a specific time span. immediately as it is CBSE
Q. 13 produced. Study 5 93 2
Takes more time to Takes less time (seconds material
process data. or milliseconds) to
process data.
( ½ mark for each point)
ŷ = ∑wixi+bias
= w1x1 + w2x2 + w3x3 + bias
Substituting values of w1, x1 , w2, x2 ,w3 , x3, bias, we get CBSE 106 –
Q. 14 ŷ = (6 X 1) + (3 X 0) + (2 X 1) – 2 Study 6 2
108
=6+0+2−2 material
=6
(1 mark for formula; 1 mark for calculations)
Generative models aim to understand and replicate the
underlying data distribution to generate new samples, CBSE
Q. 15 while discriminative models focus on distinguishing Study 7 125 2
between different data classes. material
(1 mark each for a correct difference)
• Collect and organize the data.
• Use proper visualization tools to present the data.
• Observe relationships between data.
Q. 16 Study 8 157 2
• Create a simple narrative hidden in the data for the
audience.
(½ mark for each point)
Page 5 of 8

Answer any 3 out of the given 5 questions in 50– 80 words each (4 x 3 = 12 marks)

Train-Test Split Cross Validation

Normally applied on Normally applied on small
large data sets data sets CBSE
Q. 17 Study 2 32,33 4
Divides the data into Divides a dataset into subsets material
training data set and (folds), trains the model on
testing data set. some folds, and evaluates its
performance on the
remaining data.

Clear demarcation on Every data point at some
training data and stage could be in either
testing data. testing or training data set.
(½ mark for each diagram; ½ mark for each correct point)

a) Velocity
• Velocity refers to the speed at which data is
generated, delivered, and analyzed.
• In the present digital world, millions of people are
accessing and storing information online, leading to
high-speed data flow. Eg: The website recording
thousands of clicks, searches, and transactions
every second reflects high data generation speed.
b) Volume
• Volume refers to the massive quantity of data
generated daily, which may range from terabytes to
exabytes.
• As online platform usage grows, the quantity of data
Q. 18 Study 5 90,91 4
stored increases exponentially. Eg: Petabytes of
orders, payment details, and product listings stored
over years represent the large volume
characteristic.
c) Variety
• Variety refers to the different types and formats of
data in Big Data — structured, semi-structured, and
unstructured.
• These diverse formats provide richer information
but require different processing techniques. Eg:
Structured product databases, semi-structured
XML/JSON order files, and unstructured reviews,
images, and videos.

Page 6 of 8

d) Veracity
• Veracity deals with the accuracy, quality, and
trustworthiness of data.
• Not all collected data is useful; data cleaning is
essential to remove errors and inconsistencies
before analysis. Eg: Removing incomplete or
duplicate records to ensure the dataset is reliable.
(½ mark for identifying each correct term ; ½ mark for
each relevant explanation)

• Advancing Deep Learning → Neural Networks with
multiple layers power Deep Learning, helping
machines understand complex patterns in large
datasets. CBSE
Q. 19 • Improving Accuracy and Efficiency → They analyze Study 6 112 4
vast data and make highly accurate predictions (e.g., material
detecting diseases from medical images), boosting
efficiency in real-world tasks.
• Supporting Autonomous Systems → Neural networks
provide the perception and decision-making
capabilities needed for autonomous systems (e.g.,
self-driving cars, robots, drones), enabling real-time
sensing, control, and safe automation.
• Personalizing Experiences → By analyzing user
preferences, Neural Networks power
recommendation systems (shopping, music, movies),
creating tailored experiences.
(1 mark for each point)
• Disruptive Training Approach : LLaMA is trained on
publicly available text and code, unlike traditional
LLMs that rely on proprietary datasets. This
promotes transparency in AI research and makes the
model more accessible. Additionally, it uses efficient
training techniques, requiring less computational
CBSE 130,
power, which improves scalability across devices.
Q. 20 Study 7 4
• Flexibility Through Multi-Model Design: 131
Meta released LLaMA in multiple versions, ranging
from 7 billion to 65 billion parameters. This provides
flexibility — smaller models can run on devices with
limited resources for everyday tasks, while larger
models handle complex NLP applications with higher
performance.
Page 7 of 8

• Impressive Results Despite Public Data: Even though
it uses open-source data, LLaMA delivers results that
are competitive with or better than larger
proprietary LLMs. It performs strongly in tasks like
text summarization and question answering, proving
the effectiveness of its training approach.

(1 mark for diagram; 1 mark for each point)
2. Rising action: The series of events that build up
to the climax of the story.
3. Climax: The most intense or important point
within the story. It is often an event in which the
fortune of the protagonist turns for the better or
worse in the story.
4. Falling action: The rest of the events that unravel
Q. 21 Study 8 154 4
after the main conflict has occurred, but before
the final outcome is decided.
5. Conclusion: The conclusion of the story where all
of the conflicts are resolved and outstanding
details are explained.
( ½ mark for identifying the term; ½ mark for brief
explanation)

Page 8 of 8

Study Materials
Notes

Model Papers Class 6 Notes

Sample Papers Class 7 Notes
Half Yearly Sample Papers Class 8 Notes

Class 9 Notes
Important Resources
Class 10 Notes
Periodic Table
Class 11 Notes
Writing Skills / Formats

Maps of India / World Class 12 Notes

Books and Solutions

NCERT Books
NCERT Book Solutions
HC Verma Chapter Wise Solutions
RD Sharma Solutions
CGBSE Solutions