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.

Duration

Input Tokens

1016

Output Tokens

407

Cost

$0.02

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_monthly_payments (
    instructor_payment_id SERIAL PRIMARY KEY,
    instructor_id INT NOT NULL REFERENCES users(user_id),
    pay_month DATE NOT NULL,
    amount DECIMAL(10, 2) NOT NULL CHECK (amount >= 0),
    paid_at TIMESTAMP DEFAULT NOW(),
    notes TEXT,
    UNIQUE (instructor_id, pay_month)
);