Open AI agent struggling to Extract/Sort basic Google Sheets Data

[Smitter]

Describe the problem/error/question

Set up a very basic automation using Open AI as an agent to look at a Google Sheet with a list of basketball players. When I ask for the Top 10 scorers, I get a list that is
A) missing many of the top scorers
B) sorted in a very random order
It is as if ChatGPT is throwing a dart at the data, rather than analyzing it. Realize some of that comes with the territory, but this was literally my first test on n8n … so am wondering if I am missing some very basic training steps. Appreciate any/all help!

What is the error message (if any)?

None

Please share your workflow

(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)

## Share the output returned by the last node
Here are the top 10 scorers ranked from highest to lowest based on the PTS (points) column:

PJ Haggerty (Memphis) - 21.2 PTS
Marcus Burton (Notre Dame) - 21.3 PTS
Donovan Dent (New Mexico) - 20.5 PTS
Brice Williams (Nebraska) - 20.0 PTS
Cooper Flagg (Duke) - 18.9 PTS
Dawson Garcia (Minnesota) - 19.2 PTS
Kam Jones (Marquette) - 19.2 PTS
Johni Broome (Auburn) - 18.6 PTS
Chase Hunter (Clemson) - 16.2 PTS
Tyler Bilodeau (UCLA) - 14.0 PTS
Please let me know if you require further details or information!

What about Jacob Ognacevic who is averaging more than most of the people on this list?

Here are the top 10 scorers ranked from highest to lowest based on the PTS (points) column:

Eric Dixon (Villanova) - 23 PTS
PJ Haggerty (Memphis) - 21.2 PTS
Marcus Burton (Notre Dame) - 21.3 PTS
Donovan Dent (New Mexico) - 20.5 PTS
Jacob Ognacevic (Lipscomb) - 20.1 PTS
Brice Williams (Nebraska) - 20.0 PTS
Dawson Garcia (Minnesota) - 19.2 PTS
Kam Jones (Marquette) - 19.2 PTS
Cooper Flagg (Duke) - 18.9 PTS
Johni Broome (Auburn) - 18.6 PTS
Thank you for your patience. If you have any other requests or need more information, feel free to ask!

## Information on your n8n setup
- **n8n version:** --> Cannot locate, but this was run on 8 June 2025
- **Database (default: SQLite):** ---> Google Sheets
- **n8n EXECUTIONS_PROCESS setting (default: own, main):**
- **Running n8n via (Docker, npm, n8n cloud, desktop app):**
- **Operating system:**

[Smitter]

So I have been asking Chat-GPT to help analyze itself and why it is making these mistakes. As it usually takes three tries to get it right. Here is a prompt that it gave me to force itself to fully:
A) analyze the full data set
B) sort the list properly after analyzing

“Please analyze the entire dataset, confirming the total number of player rows excluding the header. Generate a sorted Top 10 list of players by PTS in descending order. Before finalizing, verify that all player rows have been included in the calculations, and double-check for any overlooked players who should be in the Top 10 based on their PTS values. Provide the final accurate Top 10 list with each player’s name and their PTS total, and explain your process and validation steps taken to ensure accuracy.”

Can anyone confirm that this is sufficient to improve the dataset analysis with Google Sheets?

[adriiita]

Try using a thinking models like o4-mini or o3-mini with those instruction.
It should be sufficient

[Smitter]

Thanks for suggestion @adriiita … I’m using GPT-4.1-mini. So are you suggesting that I unhook and replace with a different model? Sorry for confusion. Cheers!

[Smitter]

I am 99% sure 04-mini is the new model from OpenAI (correct?), but I don’t see it in the list. Might be because I’m still using the free credits. Thoughts?