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

13s

Input Tokens

860

Output Tokens

353

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

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