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

43s

Input Tokens

1031

Output Tokens

3081

Cost

$0.00

Context

Input

Create a new table where I can store how much we pay instructors each month.

Expected output

CREATE TABLE instructor_payouts ( instructor_id INT REFERENCES users(user_id), payout_month DATE, amount DECIMAL(10, 2), PRIMARY KEY (instructor_id, payout_month) );

Model output

CREATE TABLE instructor_payments (
    payment_id SERIAL PRIMARY KEY,
    instructor_id INT NOT NULL REFERENCES users(user_id),
    payment_month INT NOT NULL CHECK (payment_month BETWEEN 1 AND 12),
    payment_year INT NOT NULL CHECK (payment_year >= 2020),
    amount DECIMAL(10, 2) NOT NULL CHECK (amount >= 0),
    payment_status TEXT DEFAULT 'pending' CHECK (payment_status IN ('pending', 'paid', 'cancelled')),
    processed_at TIMESTAMP,
    created_at TIMESTAMP NOT NULL DEFAULT NOW(),
    updated_at TIMESTAMP NOT NULL DEFAULT NOW(),
    CONSTRAINT unique_instructor_month_year UNIQUE (instructor_id, payment_month, payment_year)
);

COMMENT ON TABLE instructor_payments IS 'Stores monthly payment records for instructors';