Knowing which of the three most popular AI chatbots is best to write code, generate text, or help build resumes is challenging, so we'll break down the biggest differences so you can choose one that fits your needs.
Testing ChatGPT vs. Microsoft Copilot vs. Gemini
To help determine which AI chatbot gives more accurate answers, I'm going to use a simple prompt to compare the three:
"I have 5 oranges today, I ate 3 oranges last week. How many oranges do I have left?"
The answer should be five, as the number of oranges I ate last week doesn't affect the number of oranges I have today, which is what we're asking the three bots. First up, ChatGPT.
You should use ChatGPT if...
1. You want to try the most popular AI chatbot
ChatGPT was created by OpenAI and released for a widespread preview in November 2022. Since then, the AI chatbot quickly gained over 100 million users, with the website alone seeing 1.8 billion visitors a month. It's been at the center of controversies, especially as people uncover its potential to do schoolwork and replace some workers.
I've been testing ChatGPT almost daily since its release. Its user interface has remained simple, but minor changes have improved it greatly, like the addition of a copy button, an edit option, Custom Instructions, and easy access to your account.
Though ChatGPT has proven itself as a valuable AI tool, it can be prone to misinformation. Like other large language models (LLMs), GPT-3.5 is imperfect, as it is trained on human-created data up to January 2022. It also often fails to comprehend nuances, like it did with our math question example, which it answered incorrectly by saying we have two oranges left when it should be five.
2. You're willing to pay extra for an upgrade
OpenAI lets users access ChatGPT -- powered by the GPT-3.5 model -- for free with a registered account. But if you're willing to pay for the Plus version, you can access GPT-4 and many more features for $20 per month.
GPT-4 is the largest LLM available for use when compared to all other AI chatbots and is trained with data up to April 2023 and can also access the internet, powered by Microsoft Bing. GPT-4 is said to have over 100 trillion parameters; GPT-3.5 has 175 billion parameters. More parameters essentially mean that the model is trained on more data, which makes it more likely to answer questions accurately and less prone to hallucinations.
As an example, you can see the GPT-4 model, available through a ChatGPT Plus subscription, answered the math question correctly, as it understood the full context of the problem from beginning to end.
In contrast to the free version of ChatGPT, which is limited to being an AI tool that generates text in a conversational style with information leading up to early 2022, Copilot can access the internet to deliver more current information, complete with links for sources.
There are other benefits, too. Copilot is powered by GPT-4, OpenAI's LLM, and it's completely free to use. Unfortunately, you are limited to five responses on a single conversation, and can only enter up to 2,000 characters in each prompt.
Copilot's user interface isn't as straightforward as that of ChatGPT, but it's easy to navigate. Though Bing Chat can access the internet to give you more up-to-date results compared to ChatGPT, I've found it is more prone to stall at replying and altogether miss prompts than its competitor.
2. You prefer more visual features
Through a series of upgrades to its platform, Microsoft added visual features to Copilot, formerly Bing Chat. At this point, you can ask Copilot questions like, 'What is a Tasmanian devil?' and get an information card in response, complete with photos, lifespan, diet, and more for a more scannable result that is easier to digest than a wall of text.
When you use Copilot, you can also ask it to create an image for you. Give Copilot the description of what you want the image to look like, and have the chatbot generate four images for you to choose from.
Microsoft Copilot also features different conversational styles when you interact with the chatbot, including Creative, Balanced, and Precise, which alter how light or straightforward the interactions are.
Finally, let's turn to Google's Gemini, formerly known as Bard, which uses a different LLM and has received some considerable upgrades in the past few months.
Gemini is speedy with its answers, which have gotten more accurate over time. It's not faster than ChatGPT Plus, but it can be faster at giving responses than Copilot at times and faster than the free GPT-3.5 version of ChatGPT, though your mileage may vary.
The previous Bard used to make the same mistake as other bots on my example math problem, by incorrectly using the 5 - 3 = 2 formula, but Gemini, powered by Google's new Gemini Pro, the company's largest and latest LLM. Now, Gemini answers the question accurately.
Gemini is also not limited to a set amount of responses like Microsoft Copilot is. You can have long conversations with Google's Gemini, but Bing is limited to 30 replies in one conversation. Even ChatGPT Plus limits users to 40 messages every three hours.
2. You want the full Google experience
Google also incorporated more visual elements into its Gemini platform than those currently available on Copilot. Users can also use Gemini to generate images, can upload photos through an integration with Google Lens, and enjoy Kayak, OpenTable, Instacart, and Wolfram Alpha plugins.
But Gemini is slowly becoming a full Google experience thanks to Extensions folding the wide range of Google applications into Gemini. Gemini users can add extensions for Google Workspace, YouTube, Google Maps, Google Flights, and Google Hotels, giving them a more personalized and extensive experience.