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

22s

Input Tokens

818

Output Tokens

1850

Cost

$0.00

Context

Input

For each dealership, rank employees by total sales amount in descending order. In the results I want to see dealership_name, employee_name , total_sales and sales_rank

Expected output

SELECT d.name AS dealership_name, e.name AS employee_name, SUM(s.sale_price) AS total_sales, RANK() OVER (PARTITION BY d.branch_id ORDER BY SUM(s.sale_price) DESC) AS sales_rank FROM sales s JOIN employees e ON s.employee_id = e.employee_id JOIN dealerships d ON s.branch_id = d.branch_id GROUP BY d.name, e.name, d.branch_id;

Model output

SELECT
d.name AS dealership_name,
e.name AS employee_name,
SUM(s.sale_price) AS total_sales,
RANK() OVER (PARTITION BY d.branch_id ORDER BY SUM(s.sale_price) DESC) AS sales_rank
FROM
    dealerships d
JOIN employees e ON d.branch_id = e.branch_id
JOIN sales s ON e.employee_id = s.employee_id AND d.branch_id = s.branch_id
GROUP BY d.name, e.name, d.branch_id
ORDER BY d.name, sales_rank;