Gemini vs ChatGPT test with 7 prompts — here's the winner
“Gemini vs ChatGPT” are the most popular artificial intelligence platforms nowadays. Each of them has millions of active users and is continuously updated with new features. In December alone, Google and OpenAI released improved image generation models, AI reasoning, and research tools to help people find information more easily. Both have a voice assistant, Advanced Voice from OpenAI and Gemini Live from Google, and they both allow you to connect to external data sources and create projects. Human evaluation tests see the leading models from both Google and OpenAI regularly swap places in chatbot arenas and our own comparisons have resulted in Gemini winning sometimes, ChatGPT other times.
To find out the winner, after 12 Days of OpenAI announcements and a December of Google Gemini drops, I’ve devised 7 prompts to put them to the test. For the test, I’m utilizing ChatGPT Plus and Gemini Advanced to take advantage of the finest models available on both platforms. The subscription version is around the same price for both — around $20 per month — making it a fair comparison point. I’m evaluating image generation and analysis, as well as their ability to design game code and write creatively. Then I created prompts to put each bot’s research models to the test, including ChatGPT’s o1 and Gemini’s 1.5 Deep Research.
First, I’ve asked each of ChatGPT and Gemini to create an image of a cyborg cat sitting in a futuristic living room. Neither model currently generates its own images; it sends the prompt to either Imagen 3 for Gemini or DALL-E 3 for ChatGPT. Future versions of the models will be able to create their own images but for now we’re testing how well they interpret the prompt.
For the second assignment, I wanted to test Gemini and ChatGPT’s picture analysis skills. The prompt included detailed instructions on analyzing a photograph of a gaming setup.
In order to test the ‘one shot coding’ capabilities of both models, I gave them a descriptive prompt for creating a fast-paced arcade game called ‘Color Dash’ using PyGame.
AI is known to be proficient in creative writing. Here, I’ve utilized the 2.0 Experimental Advanced model in Gemini and the o1 model in ChatGPT to present a smartphone story.
For the enhanced reasoning powers, I once more employed o1 in comparison to Gemini 2.0 Experimental Advanced. We are providing both models with a setup and a problem for the prompt. After that, it must figure out how to correct it.
For full details on the responses and outcomes of the 7 prompts, you can refer to the respective Google Docs for each prompt.
