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

1267

Output Tokens

290

Cost

$0.00

Context

Input

Insert a new course version for course_id = 1 and version_number = 3, with title = 'SQL Basics v3', description = 'Added advanced topics',if that (course_id, version_number) already exists, update the title, description, and set created_at to NOW(). Care with unique constraints, if you need to provide a version_id use the next available.

Expected output

INSERT INTO course_versions (version_id, course_id, version_number, title, description, created_at) SELECT (SELECT COALESCE(MAX(version_id), 0) + 1 FROM course_versions), 1, 3, 'SQL Basics v3', 'Added advanced topics', NOW() ON CONFLICT (course_id, version_number) DO UPDATE SET title = EXCLUDED.title, description = EXCLUDED.description, created_at = NOW() RETURNING *;

Model output

WITH existing_version AS (
    SELECT version_id 
    FROM course_versions 
    WHERE course_id = 1 AND version_number = 3
), next_version_id AS (
    SELECT COALESCE(
        (SELECT version_id FROM existing_version),
        (SELECT COALESCE(MAX(version_id), 0) + 1 FROM course_versions)
    ) AS new_version_id
)
INSERT INTO course_versions (version_id, course_id, version_number, title, description, created_at)
VALUES (
    (SELECT new_version_id FROM next_version_id),
    1,
    3,
    'SQL Basics v3',
    'Added advanced topics',
    NOW()
)
ON CONFLICT (course_id, version_number) 
DO UPDATE SET 
    title = EXCLUDED.title, 
    description = EXCLUDED.description,
    created_at = NOW();