SQL

Natural language to SQL query generation evaluates text-to-query fidelity and schema reasoning. This task is particularly relevant for analytics chat assistants and simplified database interfaces where users need to query data using natural language. Models must understand both the intent behind the question and the structure of the underlying database schema.

100
Duration
1m 22s
Input Tokens
956
Output Tokens
201
Cost
$0.00
Context
Input
I am in the class with teacher Amanda Svensson, I can't find the link to the video for the last lesson. Can you provide me with it?
Expected output
SELECT l.video_url FROM lessons l JOIN courses c ON l.course_id = c.course_id JOIN users u ON c.instructor_id = u.user_id WHERE u.name = 'Amanda Svensson' AND l.order_index = (SELECT MAX(order_index) FROM lessons l2 WHERE l2.course_id = c.course_id);
Model output
WITH user_course AS (
    SELECT e.course_id
    FROM enrollments e
    INNER JOIN courses c ON e.course_id = c.course_id
    INNER JOIN users instr ON c.instructor_id = instr.user_id
    WHERE instr.name = 'Amanda Svensson'
    AND e.user_id = $1
    AND e.status = 'active'
    ORDER BY e.enrolled_at DESC
    LIMIT 1
)
SELECT l.video_url
FROM lessons l
INNER JOIN user_course uc ON l.course_id = uc.course_id
ORDER BY l.order_index DESC
LIMIT 1;