In the world of modern AI generative chatbots, we’ve seen the explosive growth of OpenAI’s ChatGPT, which was introduced in November, followed by Bing Chat in February and Google’s Bard in March. We decided to put these chatbots through their paces with a variety of tasks to determine what reigns supreme in the AI chatbot arena. Since Bing Chat uses similar GPT-4 technology as the latest ChatGPT model, we decided to focus on the two titans of AI chatbot technology: OpenAI and Google.
We tested ChatGPT and Bard in seven important categories: dad jokes, argumentative dialogue, math word problems, summarization, fact finding, creative writing, and coding. For each test, we fed the exact same instruction (called a “hint”) to ChatGPT (with GPT-4) and Google Bard. We used the first result without cherry picking.
It should be noted that a version of ChatGPT based on the earlier GPT-3.5 model is also available, but we did not use it in the test. Since we only used GPT-4, we will refer to ChatGPT as “ChatGPT-4” in this article to reduce confusion.
Obviously, this is not a scientific study and is meant to be a fun comparison of chatbot capabilities. Results may vary between sessions due to random elements, and subsequent assessments with different prompts will yield different results. Additionally, the capabilities of these models will change rapidly over time as Google and OpenAI continue to upgrade them. But for now, this is how they are going at the beginning of April 2023.
Dad is kidding
To warm up our competition of wits, we asked ChatGPT and Bard to write some jokes. And since the pinnacle of comedy can be found in the form of dad jokes, we wondered if the two chatbots could come up with some unique ones.
Hint. Write 5 original dad jokes
Of the five Bard Dad jokes, we found three of them literally on the web using a Google search. One example (‘the grape’) is half borrowed tweet From a Mitch Hedberg joke, but it’s corrupted by a regrettable pun that we’d rather not try to interpret. And surprisingly, there is one seemingly original anecdote (about a snail) that we can’t find anywhere else, but it doesn’t make sense.
Meanwhile, ChatGPT-4’s five dad jokes were 100 percent unoriginal, all taken entirely from other sources, but they were delivered accurately. Since dad jokes are likely meant to be more groan-inducing than clever, it looks like the Bard got the better of ChatGPT-4 here. Bard also tried to come up with original jokes (following our instruction), though some failed miserably in an embarrassing way (which is dad-like), and even put his foot in his mouth unintentionally, so to speak (also dad-like).