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

20s

Input Tokens

965

Output Tokens

2092

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 IF NOT EXISTS instructor_monthly_payments (
  payout_id SERIAL PRIMARY KEY,
  instructor_id INT NOT NULL REFERENCES users(user_id),
  year INT NOT NULL CHECK (year >= 2000),
  month INT NOT NULL CHECK (month >= 1 AND month <= 12),
  total_amount DECIMAL(12, 2) NOT NULL CHECK (total_amount >= 0),
  paid_at TIMESTAMP WITHOUT TIME ZONE DEFAULT NOW(),
  UNIQUE (instructor_id, year, month)
);