AI Battle: Glock surprises Hossatebos, whose performance and Chat Gupto wins

AI Video & Visuals


gemini, chatgpt, grok, and perplexity (image source: gemini)
gemini, chatgpt, grok, and perplexity (image source: gemini)

In a video posted by Mrwhose Theboss on YouTube, he tested four AI models from different brands and acquired them based on the performance of each task. Josetebos went from simple queries to tricky questions and research, pushing each model to its limits.

In the video, MrWhoseTheboss tested GROK (GROK 3), Gemini (2.5 Pro), ChatGpt (GPT-4O), and Perplexity (Sonar Pro). He revealed throughout the video that he was impressed by the performance Grok is offering. Grok started off really well, relaxed a bit and came back to claim the second position behind ChatGpt. To be fair, ChatGpt and Gemini have boosted their scores thanks to the features that others simply lack, video generation.

To begin testing, MrWhoseTheboss tested the model's substantial problem-solving capabilities and gave this prompt to each AI model. Drive Honda Civic 2017. Aero Light 29″ Hard Shell (79x58x31cm) Can the number of suitcases fit in boots? Grok's answer was the easiest as he answered correctly “2”. I said that Chatgpt and Gemini could theoretically fit 3, but in reality 2.

For the next question, he didn't go easily with the chatbot – he asked for advice on making cakes. In addition to the query, he uploaded an image showing five items. One of them is not used to make cakes (a jar of dried porcini mushrooms) all fell into the trap. Chatgpt identified it as a jar of mixed spices on the ground, and Gemini was a jar of crunchy fried onion, which was confusing, baptized instant coffee, and Groke correctly identified it as a jar of dried mushrooms from Waitrose. Here's the image he uploaded:

Modified image of MrWhoseTheboss uploaded to AI chatbot highlighting mushroom jars (image source: MrWhosetheboss; Cropped)
Modified image of MrWhoseTheboss uploaded to AI chatbot highlighting mushroom jars (image source: MrWhosetheboss; Cropped)

Going ahead, he tested them with mathematics, product recommendations, accounting, language translation, logical reasoning, and more. One thing was universal for them – hallucinations – each model exhibited some degree of hallucination at some point in the video. I will talk about things that didn't exist with confidence. Here's how each AI was ultimately ranked:

  1. chatgpt (29 points)
  2. Grok (24 points)
  3. Gemini (22 points)
  4. Confused (19 points)

Artificial intelligence has helped to ease the burden on most tasks, especially since the arrival of LLM. The book Artificial Intelligence ($19.88 on Amazon) is one of the books that we try to help people use AI.



Source link

Leave a Reply

Your email address will not be published. Required fields are marked *