Running GPT 5.2 side-by-side against Gemini, Claude, Deepseek and Grok

I ran the same prompt through GPT 5.2, Gemini 3 Pro Preview, Claude Sonnet 4.5, Grok 4, and DeepSeek V3.1, then was able to do an AI analysis on them. Of course GPT 5.2 came out on top. Feel free to plug and play with your own prompt to see the results.

https://preview.redd.it/elwml3bndt6g1.png?width=1102&format=png&auto=webp&s=8ca209d61765c1a7b1fe48fad41537b9bfced2b4