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.

Duration

39s

Input Tokens

980

Output Tokens

2499

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

SELECT c.course_id,
       c.title AS course_title,
       l.lesson_id,
       l.title AS lesson_title,
       l.video_url
FROM courses c
JOIN users u ON u.user_id = c.instructor_id
JOIN LATERAL (
    SELECT lesson_id, title, video_url, order_index
    FROM lessons
    WHERE course_id = c.course_id
      AND is_draft = FALSE
      AND video_url IS NOT NULL
    ORDER BY order_index DESC NULLS LAST, lesson_id DESC
    LIMIT 1
) l ON TRUE
WHERE u.name = 'Amanda Svensson'
  AND c.is_published = TRUE;