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

Input Tokens

961

Output Tokens

269

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 rank AS (
  SELECT branch_id, employee_id, SUM(sale_price) AS total_sales
  FROM sales
  GROUP BY branch_id, employee_id
)

SELECT dealerships.name AS dealership_name, employees.name AS employee_name, rank.total_sales, ROW_NUMBER() OVER (PARTITION BY dealerships.name ORDER BY rank.total_sales DESC) AS sales_rank
FROM dealerships
JOIN rank ON dealerships.branch_id = rank.branch_id
JOIN employees ON dealerships.branch_id = employees.branch_id