Opper

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.

SQL – mistral/mistral-medium-2508-eu Task | Opper AI

Input Tokens

24446

Output Tokens

5567

Duration

138424.297

Cost

0

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 amanda_courses AS (
    SELECT c.course_id
    FROM users u
    JOIN courses c ON u.user_id = c.instructor_id
    WHERE u.name = 'Amanda Svensson'
),
last_lesson AS (
    SELECT l.lesson_id, l.video_url, l.order_index
    FROM lessons l
    JOIN amanda_courses ac ON l.course_id = ac.course_id
    ORDER BY l.order_index DESC
    LIMIT 1
)
SELECT video_url
FROM last_lesson;