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

990

Output Tokens

220

Cost

$0.00

Context

Input

Show the names of customers who paid more than the average sale price for the vehicles they bought.

Expected output

SELECT c.name FROM customers c JOIN sales s ON c.customer_id = s.customer_id WHERE s.sale_price > (SELECT AVG(s2.sale_price) FROM sales s2 WHERE s2.vehicle_id = s.vehicle_id);

Model output

WITH CustomerAvgSale AS (
  SELECT
    s.customer_id,
    AVG(s.sale_price) AS avg_sale_price
  FROM sales AS s
  GROUP BY
    s.customer_id
)
SELECT DISTINCT
  c.name
FROM customers AS c
JOIN sales AS s
  ON c.customer_id = s.customer_id
JOIN CustomerAvgSale AS cas
  ON s.customer_id = cas.customer_id
WHERE
  s.sale_price > cas.avg_sale_price;