One of the things I’ve been experimenting with in AI is taking things other people do and seeing how well the AI works. In this case, I took a Prompt from Louis and tried to see how well it worked. This post describes the results from a few models.
This is part of a series of experiments with AI systems.
The Challenge Using Claude
Louis was using an AI to generate some test data to play with the new Regex functionality in SQL Server 2025. He put this in ChatGPT: “create a set of random string data with 1000 rows for a sql server table named RegExTest. It should insert data into a column named Value”.
He had mixed results with ChatGPT, which I tend not to use. Instead, I tried this in Claude. I like Claude as I get an explanation separate from the code. Here’s a view of the page:
Here’s the code, which is nice because I could steal certain patterns out of here if I had the need. The explanation was also good, and I’ve reproduced that here:
This SQL script creates 1000 rows of diverse random string data for your RegExTest table. The data includes various patterns that are useful for testing regular expressions:
- Email addresses (user@domain.com)
- Phone numbers ((123) 456-7890)
- Dates (MM/DD/YYYY)
- Mixed alphanumeric with special characters (ABC-123_XYZ)
- Numeric strings (123456)
- URL patterns (https://www.example.com/path)
- Code patterns (AB12C345)
- Words with spaces (Hello World)
- Mixed case strings (AbCdEf123)
- Random alphanumeric strings
The script uses a recursive CTE to generate 1000 rows and applies different string generation patterns based on the row number modulo operations. This ensures you get a good variety of data types to test your regular expressions against.
The script also includes table creation (if it doesn’t exist) and verification queries to confirm the data was inserted successfully.
There was an issue in the else part of the CASE. The last CONCAT call only had the first parameter and CONCAT needs two parameters, so I copy/pasted the 2nd parameter from the last THEN statement, which worked fine. In this case, that parameter was an acceptable choice to create a random alpha string.
Perplexity
I got a very weak result from Perplexity. Essentially, write insert statements, though you could use a script.
I didn’t see a script, so I asked. I got this.
Here’s the SQL Code:
That’s weak. It works, but it’s weak and I think I could have written that in not much more time than the AI took.
It did end with this sentence: Let me know if you want the script in another format or with different string lengths!
I did and then got a series of different scripts for different formats, but each was producing a separate 1000 rows of only that format.
DeepSeek
I download the DeepSeek coder model and decided to try that. The basic prompt was disappointing. The model basically wanted to use Python and only imported modules without other code.
When I said that and asked for code, I got more details, but with the script separated out into sections. The top seemed to repeat a bit.
Then I got each part of the script.
I didn’t run this, but it’s a reasonable way to do things for developers. For data people, this seems like overhead.
I asked for SQL, and got a script for Oracle, but more interesting, the code is for 1000 rows, but the comments say ten thousand. Can’t the GenAI count?
I asked to change this to SQL Server and got this code.
I don’t know what to say except that I’m disappointed in the local deepseek model, which is not only slow, but hasn’t produced a good answer.
Summary
Claude clearly wins this experiment.
