Opper

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.

SQL – cerebras/llama-4-maverick-17b-128e-instruct Task | Opper AI

Input Tokens

0

Output Tokens

0

Duration

0

Cost

0

Context

Input

Show customer names and the number of service records (as service_count) for their vehicles ordered alphabetically, only customers with service records (not 0)

Expected output

SELECT c.name, COUNT(*) AS service_count FROM customers c JOIN sales s ON c.customer_id = s.customer_id JOIN service_records sr ON s.vehicle_id = sr.vehicle_id GROUP BY c.name ORDER BY c.name;

Model output

SELECT c.name, COUNT(sr.record_id) AS service_count FROM customers c JOIN sales sa ON c.customer_id = sa.customer_id JOIN vehicles v ON sa.vehicle_id = v.vehicle_id JOIN service_records sr ON v.vehicle_id = sr.vehicle_id GROUP BY c.name HAVING COUNT(sr.record_id) > 0 ORDER BY c.name ASC;