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

1196

Output Tokens

224

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),
    payment_amount DECIMAL(10, 2) NOT NULL,
    payment_month INT CHECK (payment_month BETWEEN 1 AND 12) NOT NULL,
    payment_year INT NOT NULL,
    payment_date TIMESTAMP DEFAULT NOW(),
    status TEXT CHECK (status IN ('pending', 'paid', 'cancelled')) DEFAULT 'pending',
    notes TEXT,
    UNIQUE (instructor_id, payment_month, payment_year)
);