Test 2 - creating a travel bingo card

This page has 0 threads | Add post

Blogs

Many people around the world enjoy and benefit from our blogs. If you're one of them - and can afford to - please make a small donation to help keep this and future blogs, exercises, skills assessment tests, tips, tutorials and videos freely available to everyone!

Some other pages relevant to these blogs include:

Classes in AI (Artificial Intelligence)

You can also book hourly online consultancy for your time zone with one of our 7 expert trainers!

Comparing how well the main AI tools deal with 5 difficult challenges Part three of a seven-part series of blogs
In what is becoming almost an annual exercise we revisit the main AI tools to see which (if any) has the edge in accomplishing 5 challenging tasks, each designed to test a different aspect of the use of AI. Which AI tools we'll test, and the 5 challenges each will face Test 1- analysing emails by importance Test 2 - creating a travel bingo card (this blog) Test 3 - creativity Test 4 - summarising and presenting information Test 5 - coding challenge to produce the longest word chains The final conclusion - not all AI tools are the same

Comparing how well the main AI tools deal with 5 difficult challenges

Part three of a seven-part series of blogs

In what is becoming almost an annual exercise we revisit the main AI tools to see which (if any) has the edge in accomplishing 5 challenging tasks, each designed to test a different aspect of the use of AI.

Which AI tools we'll test, and the 5 challenges each will face
Test 1- analysing emails by importance
Test 2 - creating a travel bingo card (this blog)
Test 3 - creativity
Test 4 - summarising and presenting information
Test 5 - coding challenge to produce the longest word chains
The final conclusion - not all AI tools are the same

Posted by Andy Brown on 11 May 2026

In this blog

ChatGPT (about 3 minutes)
Claude (about 3 minutes)
Copilot (about 2 minutes)
Gemini (about 30 seconds)
Conclusions and winner/loser

The range of results from this test was much wider!

ChatGPT (about 3 minutes)

I think ChatGPT did a great job with this:

I particularly like the dragon and the flyng pig!

ChatGPT also got the pictures just right for the audience. I'm impressed.

Claude (about 3 minutes)

Claude produced two separate cards with well-chosen images, but the drawing and labels leave a bit to be desired:

Claude has gone for child-like drawings, rather than drawings for a child.

There are a few anomalies:

This isn't a great representation of a service station.

It's worth also noting that the ambulance picture is completely missing ...

Copilot (about 2 minutes)

This was a good answer, although irritatingly I only get one image at a time:

The Overhoay sign label is wrong, but everything else seems really good.

Copilot then explains that it can't create more than one image at a time, but goes on to give ideas for the second one with lots of useful follow-up text:

Copilot even then offers to personalise the cards with the children's names.

I think Copilot got the pictures and audience just right, but it's a shame it could only do one picture at a time.

Gemini (about 30 seconds)

Gemini's cards were by far the quickest - and it showed:

Superficially everything seems good, but ...

Gemini has created 4 cards, not 2, with subtle differences between each of the two pairs. Most of the pictures make sense, but not all:

The legend isn't a great description of the picture.

I also don't like the lack of subtlety in the labelling:

I think the children can work out this is meant to be impossible and funny.

On the plus side, Gemini was by some way the quickest AI tool for this task.

Conclusions and winner/loser

This is hard to judge - I've done my best!

Who	Score out of ten	Why
ChatGPT	9	The only answer which you could use without modification - good pictures and good labelling.
Claude	6	A good choice of pictures, but poor drawings and poor labelling (if this had been done by a human, their work called be called sloppy).
Copilot	8	Only one set of images at a time with a few glitches, but good choice of pictures and good labelling on the whole.
Gemini	7	Commendably quick, but with lots of mistakes (and also the only one not to get the audience right, I thought).

What is really amazing about this is how far AI has come in a couple of years. I used to do a variation of this prompt on a course because I knew the answers would generate so much laughter, but sadly this is yet another instance where AI tools have learned not to hallucinate.

Parts of this blog
Which AI tools we'll test, and the 5 challenges each will face Test 1- analysing emails by importance Test 2 - creating a travel bingo card (this blog) Test 3 - creativity Test 4 - summarising and presenting information Test 5 - coding challenge to produce the longest word chains The final conclusion - not all AI tools are the same

Some other pages relevant to these blogs include:

Classes in AI (Artificial Intelligence)

You can also book hourly online consultancy for your time zone with one of our 7 expert trainers!

This blog has 0 threads

Add a new post

ALL BLOGS

ARTIFICIAL INTELLIGENCE BLOGS

ARTIFICIAL INTELLIGENCE (AI) BLOGS

ChatGPT (about 3 minutes)

Claude (about 3 minutes)

Copilot (about 2 minutes)

Gemini (about 30 seconds)

Conclusions and winner/loser

Head office

London

Manchester