Is GPT-4o Better Than GPT-4?

I have a good understanding of using ChatGPT. I know how people use it, I know how I use it. So it was pretty easy to come up with use cases for the experiment.

I’ll be testing GPT-4 against GPT-4o doing:

• Information Retrieval

• Writing With Contextual Accuracy

• Language Processing

• Creative Storytelling

1/ Information Retrieval

The first test is to summarize an article and provide me with key takeaways. Here’s the prompt I’ll be using with both models.

Summarize article from URL: https://openai.com/index/hello-gpt-4o and provide key takeways.

Winner: GPT-4o
Reason: Included both summary and key takeaways.

2/ Writing With Contextual Accuracy

I’ll prompt ChatGPT to write a persuasive ad copy for this test. I’ll provide context and constraints to see if the AI will follow it.

As a direct business copywriter, your task is to write a Facebook ad copy for a [product] that targets [target audience]. Utilize a [tone] and [language] that resonate with the audience. At the end of the copy, incorporate a humorous Call-to-Action (CTA) that encourages the audience to take action.

Product: vegan chocolate
Target Audience: Busy moms in their 30s
Tone: Desperate
Language: Overusing Buzzwords

Winner: GPT-4
Reason: GPT-4o hallucinated the answer.

3/ Language Processing

Let’s go for the next task. This one is useless for real-life scenarios, but I want to have fun and see how the models will perform. Here’s the prompt.

You'll be given a text. Your task is to replace every 3rd word in that text with the closest synonym. Respond only with a new text.

"One day, Hulk decided he was tired of smashing things and wanted to try something different, so he opened a bakery called "Hulk's Smash Cakes." The cakes were delicious but getting them to the customers in one piece was a challenge since Hulk's gentle touch was still like a minor earthquake."

Winner: GPT-4
Reason: GPT-4o failed the task.

4/ Creative Storytelling

We’ll wrap it up with a creative task. I’ll prompt ChatGPT to come up with a story, but I’ll be very specific on the details.

Come up with a bedtime story that consists of 10 sentences. 

- The story will have male hero and female antagonist.
- The antagonist will come up with victorious.
- The story will have positive message.
- The story will have humorous ending.
- The story will have simple plot.
- The story will be set in future.
- The story will be written at 3rd grade English level.

If you look at the prompt, my details are a bit of a pain in the ass. Anyway, let’s see how both models performed.

Winner: GPT-4o
Reason: GPT-4o didn’t follow constraints.

5/ Takeaway

I did 4 tests in total. And they resulted in a tie. But there’s one key takeaway that I noticed.

• GPT-4o performed better on simple and creative tasks.

• GPT-4 performed better on complex tasks with a lot of context.

CAN’T MISS

• Prompts for project management

• Prompts for sales

• Prompts for job search

• Prompts for your resume

All the prompts are available in our FREE prompt directory.

Psst: Do you want me to cover a specific use case? Hit “reply“ and let me know.

MEMES OF THE WEEK

LET’S HEAR IT!