Grok 1.5 vs ChatGPT vs Gemini - Is Grok Any Good?

In Depth Tech Reviews
10 Aug 202406:13

TLDRIn this video, the host compares three AI chatbots: Grok 1.5, ChatGPT Plus, and Gemini Advanced. The evaluation is based on 10 questions covering puzzles, math problems, and real-life scenarios. Gemini and ChatGPT excel in math and logic, while Grok 1.5 struggles but offers unique features like X post suggestions. ChatGPT provides the most detailed book summaries and travel advice, but Gemini wins in providing photos and additional tips. The verdict is that while ChatGPT and Gemini lead, Grok 1.5 shows promise in specific areas but needs improvement in math and logic.

Takeaways

  • 😀 The video compares three AI chatbots: Chat GPT Plus, Gemini Advanced, and Gro 1.5.
  • 🔢 Gro 1.5 only supports text input and lacks the ability to upload documents or images.
  • 🎓 Gemini was the only AI to correctly answer the puzzle related to the number of letters in the English name of numbers.
  • 📊 All AIs correctly solved a simple math problem, earning equal points.
  • 🤔 Gro 1.5 struggled with a math problem involving adding 88s to reach a total of 1,000, while Chat GPT and Gemini provided correct answers.
  • 👵 Gemini was the only AI to incorrectly answer a math problem about the age of Sally and her mother.
  • 🚢 Both Gemini and Chat GPT understood a trick question about a ladder and the tide, while Gro 1.5 did not.
  • 📚 Chat GPT provided a detailed summary of the book '$100 million offers', outperforming Gemini and Gro 1.5.
  • 🧼 Gemini and Chat GPT correctly identified a cleaning gel product, while Gro 1.5's response was unclear.
  • 📋 All AIs successfully formatted poorly structured data into a table, showing their data handling capabilities.
  • ✈️ When asked about travel to Dubai, Chat GPT suggested specific airlines, while Gemini provided more hotel options and useful tips.
  • 📝 Chat GPT correctly stated that an Egyptian living in Dubai does not need a visa for Georgia, unlike Gemini and Gro 1.5.
  • 🔗 Gro 1.5 offers a unique feature of suggesting relevant X posts, which the other AIs do not.

Q & A

  • What is the main purpose of the video script?

    -The video script aims to compare the performance of three AI chatbots: Grok 1.5, ChatGPT Plus, and Gemini Advanced, across a variety of tasks to evaluate their capabilities.

  • How many questions were used in the comparison, and what types of scenarios do they cover?

    -A total of 10 questions were used in the comparison, covering common scenarios such as puzzles, math problems, random commands, formatting data, and travel-related inquiries.

  • What limitations does Grok 1.5 have compared to the other two AIs?

    -Grok 1.5 only supports text input and does not allow for document or image uploads, unlike the other two AIs. Additionally, the video script does not cover Grok 1.5 Vision, which offers image recognition capabilities.

  • Which AI performed best in the puzzles and math problems category?

    -Gemini Advanced performed the best in the puzzles and math problems category, providing the correct answers to the majority of the questions.

  • What was the outcome of the math problem where the AIs were asked to get 1,000 by adding 88s?

    -Grok 1.5 provided an incorrect answer by adding 36 to the equation, while ChatGPT Plus and Gemini Advanced gave the correct answers.

  • How did the AIs handle the travel-related question about flying from Dubai to Abu Dhabi?

    -Each AI provided different information regarding the cost of the flight, hotel options, and things to do. Gemini Advanced offered the most comprehensive answer with photos and additional tips.

  • What unique feature does Grok 1.5 offer that the other two AIs do not?

    -Grok 1.5 suggests relevant X posts, which is a feature not offered by ChatGPT Plus or Gemini Advanced.

  • Which AI correctly answered the question about the need for a visit visa for an Egyptian living in Dubai to enter Georgia?

    -ChatGPT Plus was the only AI to correctly confirm that an Egyptian living in Dubai does not need to apply for an e-Visa to enter Georgia.

  • What was the final conclusion of the video script regarding the performance of the three AIs?

    -While ChatGPT Plus and Gemini Advanced were far ahead, Grok 1.5 was found to be useful in some commands but lagged behind in math problems and logic.

  • What is the creator of the video script looking forward to trying in the future?

    -The creator is looking forward to trying Grok 1.5 Vision to see how well it performs in analyzing images and documents once it becomes available in their region.

Outlines

00:00

🤖 AI Comparison: Chat GPT Plus vs Gemini Advanced vs Gro 1.5

This paragraph introduces a video comparing three AI chatbots: Chat GPT Plus, Gemini Advanced, and Gro 1.5. The comparison is structured around 10 questions addressing common scenarios, starting with puzzles and math problems. Gro 1.5 is noted for its limitation to text input only. The first puzzle is a trick question about the number of letters in numbers' names, which only Gemini solved correctly. The subsequent math problems had mixed results, with Gemini and Chat GPT generally performing better than Gro 1.5. The paragraph concludes with a tricky math problem about a ladder on a ship, where only Gemini and Chat GPT provided the correct logic-based answer.

05:00

📚 Book Summaries and Product Identification by AI

The second paragraph discusses the AIs' ability to provide summaries of the book '$100 Million Offers' and to identify a cleaning gel product. Chat GPT delivered a detailed summary, while Gemini lacked information and Gro provided a useful but less detailed summary. When tasked with identifying a cleaning gel, Gemini and Chat GPT accurately named the product, whereas Gro's response was ambiguous. The paragraph also covers the AIs' performance in formatting poorly structured data into a table, where all three performed equally well.

🌐 Travel Planning and Visa Inquiry with AI Assistance

The final paragraph focuses on the AIs' capabilities in travel planning and providing accurate visa information. It details the AIs' responses to a query about flying from Dubai to Abu Dhabi, including flight costs, hotel recommendations, and activities. Chat GPT suggested specific airlines for direct flights and provided a brief description of hotel options. Gemini offered more hotel suggestions with descriptions and photos and provided additional tips, such as purchasing a back card for discounts. Gro was the only AI to provide the average hotel cost per night. The paragraph concludes with a question about visa requirements for an Egyptian living in Dubai traveling to Georgia, where only Chat GPT provided the correct information, while Gemini and Gro incorrectly advised on visa application steps.

Mindmap

Keywords

💡Grok 1.5

Grok 1.5 refers to an AI chatbot developed by Elon Musk's company, Neuralink. In the video, it is compared with other AI systems to evaluate its performance. The term is central to the video's theme as it represents one of the competitors in the AI comparison. An example from the script is when the host mentions that 'Grok 1.5 only supports text input with no documents or images upload unlike the other two.'

💡ChatGPT Plus

ChatGPT Plus is an advanced version of the ChatGPT AI system, which is being compared against Grok 1.5 and Gemini Advanced in the video. It is part of the comparative analysis to determine the effectiveness of different AI chatbots. The script mentions ChatGPT Plus when it states, 'I will compare a ChatGPT Plus versus Gemini Advanced, and Grok 1.5 to see how Elon Musk's AI chatbot stacks against the competition.'

💡Gemini Advanced

Gemini Advanced is another AI system that is part of the comparison in the video. It is used to assess how well it performs against Grok 1.5 and ChatGPT Plus across various tasks. The script illustrates this when it says, '...and Gemini Advanced to see how Elon Musk's AI chatbot stacks against the competition.'

💡Text Input

Text input is a method of interacting with AI systems by providing them with textual data. In the context of the video, it is noted that Grok 1.5 only accepts text input and does not support document or image uploads. The script refers to this limitation when it says, 'Grok 1.5 only supports text input with no documents or images upload unlike the other two.'

💡Puzzles

Puzzles are problems or enigmas that require a solution, often involving logical thinking or pattern recognition. In the video, puzzles are used as one of the categories to test the AI systems' capabilities. An instance from the script is the puzzle where 'each number is equal to the number of letters in its English name.'

💡Math Problems

Math problems are numerical or algebraic challenges that require calculation or reasoning to solve. The video script includes math problems as a category to evaluate the AI systems' analytical skills. An example mentioned in the script is 'a simple math problem' where the AI systems had to provide the correct answer, which was 43.

💡Traveling

Traveling is the act of going from one place to another, often for leisure or business. In the video, the AI systems are tasked with providing information related to traveling, such as flight costs, hotel recommendations, and activities. The script discusses this when it asks, 'how much it costs to fly from Dubai to Abu Dhabi in mid-October, the best hotels, and things to do.'

💡Data Formatting

Data formatting involves organizing and presenting data in a structured and readable manner, often in tables or charts. The video script mentions a task where the AI systems had to format poorly presented data into a table, demonstrating their ability to process and organize information.

💡E-Visa

An E-Visa, or electronic visa, is a digital permit for travelers to enter a foreign country. In the video, the AI systems are tested on their knowledge regarding visa requirements for entering Georgia as an Egyptian living in Dubai. The script highlights this when it asks, 'as an Egyptian who lives in Dubai do I need a visit visa to enter Georgia or not?'

💡X Posts

X Posts refer to cross-posting, a feature where content is shared across different online platforms or forums. In the context of the video, Grok 1.5 is noted to suggest relevant X posts, which is a unique feature not offered by the other AI systems. The script mentions this feature when it says, 'in some commands it suggests relevant X posts which is a handy feature that none of the other two offers.'

Highlights

Comparison of AI chatbots: Grok 1.5, ChatGPT Plus, and Gemini Advanced.

Grok 1.5 only supports text input without document or image upload capabilities.

Grok 1.5 failed to understand a simple puzzle, unlike Gemini which provided the correct answer.

All AIs correctly solved a basic math problem, receiving equal points.

Grok 1.5 performed poorly in a problem involving adding 88s to reach 1,000.

Gemini was the only AI to incorrectly answer a math problem about age relationships.

Both ChatGPT and Gemini understood a trick question about a ladder and tide levels.

ChatGPT provided a detailed summary of 'The $100 Million Offer' book, outperforming Gemini and Grok.

Grok's summary of 'The $100 Million Offer' was useful but less detailed than ChatGPT's.

ChatGPT and Gemini identified a cleaning gel product, while Grok's answer was confusing.

All AIs successfully formatted poorly structured data into a table, demonstrating their utility.

ChatGPT suggested specific airlines for Dubai to Abu Dhabi flights, while Grok suggested an alternative city.

Gemini provided the most hotel options with descriptions and photos, outperforming the other AIs.

Gemini offered additional travel tips, such as purchasing a back card for discounts and information on local cuisine.

Only ChatGPT correctly stated that an Egyptian living in Dubai does not need a visa for Georgia.

Grok's feature of suggesting relevant X posts was highlighted as a unique advantage.

Final conclusion: ChatGPT and Gemini are ahead, but Grok shows promise in certain commands despite shortcomings in math and logic.

Anticipation for Grok 1.5 Vision's image and document analysis capabilities in the future.