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

28s

Input Tokens

960

Output Tokens

976

Cost

$0.00

Context

Input

Which students joined this year and already finished a lesson?

Expected output

SELECT DISTINCT u.name FROM users u JOIN completions c ON u.user_id = c.user_id WHERE u.role = 'student' AND u.created_at >= DATE_TRUNC('year', CURRENT_DATE);

Model output

SELECT u.user_id, u.name, u.email, u.created_at
FROM users u
WHERE u.role = 'student'
  AND u.created_at >= date_trunc('year', CURRENT_DATE)
  AND u.created_at < date_trunc('year', CURRENT_DATE) + INTERVAL '1 year'
  AND EXISTS (
    SELECT 1
    FROM completions c
    WHERE c.user_id = u.user_id
  );