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

1191

Output Tokens

170

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