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

1022

Output Tokens

280

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 REFERENCES users(user_id),
    amount DECIMAL(10, 2) NOT NULL,
    payment_month DATE NOT NULL,
    payment_date TIMESTAMP DEFAULT NOW(),
    status TEXT CHECK (status IN ('pending', 'paid', 'failed')) DEFAULT 'pending',
    notes TEXT,
    CONSTRAINT fk_instructor FOREIGN KEY (instructor_id) 
        REFERENCES users(user_id) ON DELETE CASCADE,
    CONSTRAINT instructor_is_instructor CHECK (
        instructor_id IN (
            SELECT user_id FROM users WHERE role = 'instructor'
        )
    )
);

CREATE INDEX idx_instructor_payments_month ON instructor_payments(payment_month);