BURSTThe recent rollout of OpenAI's GPT-5 model has not been going well, to say the least. Users have made vociferous complaints about everything from the new model's more sterile tone to its supposed lack of creativity, increase in damaging confabulations, and more. The user revolt got so bad that OpenAI brought back the previous GPT-4o model as an option in an attempt to calm things down.
To see just how much the new model changed things, we decided to put both GPT-5 and GPT-4o through our own gauntlet of test prompts. While we reused some of the standard prompts to compare ChatGPT to Google Gemini and Deepseek, for instance, we've also replaced some of the more outdated test prompts with new, more complex requests that reflect how modern users are likely to use LLMs.
These eight prompts are obviously far from a rigorous evaluation of everything LLMs can do, and judging the responses obviously involves some level of subjectivity. Still, we think this set of prompts and responses gives a fun overview of the kinds of differences in style and substance you might find if you decide to use OpenAI's older model instead of its newest.