ChatGPT vs. Gemini: The Playful Battle of Clever AI Companions

8.05.2024 | Tech Talk | 0 comments

Gemini vs. ChatGPT: What's the difference?

ChatGPT took early lead among AI-generated chatbots before Google answered with Gemini, formerly Bard. While ChatGPT and Gemini perform similar tasks, there are differences.

OpenAI introduced ChatGPT in November 2022, sparking a tremendous amount of interest in generative AI. ChatGPT gained so much attention that GenAI became a dominant theme in the tech world in 2023.

Microsoft backed OpenAI at the start of 2023 by pledging a multimillion-dollar, multiyear investment to accelerate OpenAI's development of its AI technology.

Google made its GenAI move in March 2023 with Bard. In February 2024, Google rebranded Bard as Gemini when it debuted an improved version of the AI chatbot.

ChatGPT and Gemini are largely responsible for the considerable buzz around GenAI, which uses data from machine learning models to answer questions and create images, text and videos. OpenAI and Google are continuously improving the large language models (LLMs) behind ChatGPT and Gemini to give them a greater ability to generate human-like text.

GenAI is still rapidly evolving, and models don't always return correct answers. Despite the common occurrence of AI hallucinations — wrong answers generated by AI — in both ChatGPT and Gemini, the tools are being adopted by businesses and consumers seeking to automate time-consuming tasks.

What are the main differences between Gemini and ChatGPT?
ChatGPT and Google Gemini have become more similar as the release of Gemini Ultra 1.0 has made it more competitive with GPT-4. Both have a free service, a nearly identically priced subscription service, and similar interfaces and use cases. The differences are largely under the hood — in their language models.

They're also used for many similar functions, and work by users typing in a query to get a response. Both raise privacy concerns about how user data can be used. However, they differ in their training models, data sources, user experiences and how they store data.

Training models
ChatGPT is built on OpenAI's GPT-3.5 or GPT-4, depending on whether it's the free version or the ChatGPT Plus paid version. Gemini has three sizes: Gemini Pro for a wide range of tasks, Gemini Ultra for highly complex tasks, and Gemini Nano for mobile devices. Ultra 1.0, which powers the subscription Gemini Advanced version, is faster and more advanced than the model used for the free Gemini Pro.

Data sources
The main difference between ChatGPT and Gemini is the data sources used to train their LLMs. GPT-3.5 uses predefined data that does not go beyond January 2022, while GPT-4 data goes up to April 2023. Gemini draws on data pulled from the internet in real time. It is tuned to select data chosen from sources that fit specific topics such as coding or the latest scientific research.

Gemini Ultra has the largest data set with 1.6 trillion parameters and a training data set of 1.56 trillion words. GPT-4 has roughly 1.5 trillion parameters and a training data set of 13 trillion tokens, which can be single characters, words or parts of words. More parameters give an LLM more capacity to learn and understand language. But both Gemini and ChatGPT are constantly expanding, and the sheer volume of parameters often translates into little difference in actual performance.

User experience
ChatGPT users can log onto the free ChatGPT with any email account. ChatGPT also includes an API that developers can use to integrate OpenAI LLMs into third-party software. It lacks a Save button, but users can copy and paste answers from ChatGPT into another application. It does have an Archive button that can list previous responses in ChatGPT's left-hand pane for quick retrieval.

Because ChatGPT-3.5 is text-based, it can't include images, videos, charts or links in its answers. It also lacks the ability to search the internet.

Because of OpenAI's close partnership with Microsoft, ChatGPT can be used through Windows apps such as Word, Excel, PowerPoint and Outlook. Also, Microsoft's Copilot AI assistants use ChatGPT-4's language model.

Gemini Pro's interface gives users a chance to like or dislike a response, opt to modify the size or tone of the response, share or fact-check the response, or export it to Google Docs or Gmail. Gemini also has a "review other drafts" option that shows alternate versions of its answer. Gemini also lets users upload images, but its ability to create images is on hold until Google improves that feature.

Google Ultra 1.0 has no API as of yet. Google does plan to integrate Gemini with its applications such as Docs, Gmail, Google Meet and Google Slides as part of its Google One AI Premium subscription. Users need a Google account for any version of Gemini.

Data storage and privacy
Both ChatGPT and Google Gemini store user data.

ChatGPT stores all prompts and queries entered. Users can review previous conversations through its archive feature. Although users can delete responses and conversations, the chatbot might continue to use these responses in its LLM for training. This raises privacy concerns when users enter personal data or proprietary information. OpenAI also discloses that ChatGPT gathers geolocation data, network activity, contact details such as email addresses and phone numbers, and device information.

According to OpenAI's privacy policy, it collects any personal information a user provides. This includes account information such as name, contact information, payment card information and transaction history. OpenAI also might disclose geolocation data to third parties such as vendors and service providers, and to law enforcement agencies if required to do so by law.

OpenAI said the user retains ownership rights of input data and owns the output, but it "may use Content to provide, maintain, develop, and improve our Services, comply with applicable law, enforce our terms and policies, and keep our Services safe."

Gemini stores conversations in a user's Google account for 18 months, but users can change the retention period to three months or 36 months in their activity settings. Gemini conversations can also appear in searches, raising privacy concerns.

Google discloses that it collects conversations, location, feedback and usage information. The Google Privacy Policy claims Google uses collected data to develop, provide, maintain and improve services, and to provide personal services such as content and ads. Customers can delete information from their account using My Google Activity, or by deleting Google products or their Google accounts.

Google said it will share information to third parties with user consent and law enforcement when required.

Which chatbot is better?
There is a bit of a GenAI arms race going on now, with OpenAI and Google making updates to their models. Google has been especially aggressive, perhaps because ChatGPT came out first and Gemini must play catch-up. With each new version of the LLMs, Google and OpenAI make significant gains over their previous versions.

Generally, ChatGPT is considered the best option for text-based tasks while Gemini is the best choice for multimedia content. However, there are other considerations, as noted in earlier sections of this article. Users can try the free versions to determine which works better for them.

There have been several in-depth reviews about the chatbots worth noting:

Researchers from Carnegie Mellon University and BerriAI benchmarked Gemini Pro against GPT-3 and GPT-4 on 10 diverse language tasks with the goal of providing an impartial in-depth analysis. They found Gemini's strengths included performance on long, complex reasoning chains and translating into non-English languages. On the downside, it struggled with mathematical reasoning — especially with large numbers — showed bias on multiple choice questions and aggressive content filtering blocked many responses. In summary, the researchers concluded Gemini Pro did not match GPT-3 and GPT-4, but "exhibits strengths in handling complexity and reasoning depth."
Ethan Mollick, an associate professor who studies AI at the Wharton School of the University of Pennsylvania, performed what he called "tasting notes" of Gemini Advanced vs. GPT-4. Mollick concluded that Gemini Advanced is the first advanced AI model that can compete with GPT-4. He said each has its strengths and weaknesses — for example, GPT-4 uses code in a more sophisticated way and is better at hard verbal tasks while Gemini is better at explanations and search. But both "are weird and inconsistent and hallucinate more than you would like."
Bernard Marr, a futurist and author of Generative AI in Practice, pointed out in a Forbes article that ChatGPT is designed to be more conversational while Gemini processes information and automates tasks more efficiently. Marr's conclusion after using ChatGPT and Gemini is that ChatGPT-4 is the more powerful chat interface but "Gemini is closing the gap …".
Neither ChatGPT nor Gemini are perfect, and their developers admit that. Both generate hallucinations and even warn users of that in their responses.
Both of the chatbots include a disclaimer on the bottom of their prompt screens. Gemini's reads: "Gemini may display inaccurate info, including about people, so double-check its responses." ChatGPT advises: "ChatGPT can make mistakes. Consider checking important information."
The Gemini FAQ on Google's website offers this valuable advice that can apply to all AI tools:
Gemini can't replace important people in your life, like family, friends, teachers or doctors.
Gemini can't do your work for you.
Gemini can't make important life decisions for you.

Google shook the AI world in early December 2023 by announcing the launch of Gemini, their next-generation language model. Coming in three sizes – Nano, Pro, and Ultra – Gemini promises to push boundaries in natural language understanding and content generation.

In their launch marketing, Google compared Gemini Ultra to OpenAI's recently released GPT-4 model. However, less fanfare surrounded the positioning of Gemini Pro against OpenAI's widely used GPT-3.5 offering. They also staged a demo for Gemini Ultra – but that’s a story for another time.

In this comprehensive analysis, we put Gemini Pro to the test across critical performance criteria like speed, accuracy, reasoning, and code generation. We also take a look at more subjective analysis such as the output quality and usefulness of the chat counterpart (ChatGPT vs Bard) when using the model.

Key Takeaways
Gemini Pro processes tokens over 2x faster than GPT-3.5, with 49.67 vs 36.14 tokens per second;
Gemini exhibits some preference towards Google's interests in open-ended content generation;
GPT-3.5 allows full customization while Gemini does not currently support fine-tuning. Akkio uses it to power AI analytics for agencies;
Gemini Pro, just like the entire family of Gemini AI Models, is multimodal, so it can handle images. GPT-3.5 can’t, at least not by default.
Google Gemini Pro Overview
In early December, Google released the Pro version of Gemini to developers via the Google Vertex AI platform and Google AI Studio.

Gemini Pro supports both text and image inputs to produce text outputs. The model comprehends 38 languages including English, Arabic, French, Spanish and Japanese. Benchmarking from developers shows Google's translation speed is up to 20 times faster than GPT-4, albeit at lower quality.

Compared to GPT-3.5's text-only inputs, Gemini Pro's ability to process images in addition to text gives it an edge in multimodal understanding.

Google Gemini comes with a 32,000 token context window, with plans to support even longer contexts forthcoming. Code examples are provided in Python, Android, Node.js and Swift – although developers have critiqued some of the snippets as outdated.

OpenAI’s GPT-3.5 Overview
GPT-3.5 is a variant of the Generative Pre-trained Transformer models developed by OpenAI. It is designed to offer a more cost-effective yet powerful option for natural language processing tasks. As a predecessor to GPT-4, it utilizes deep learning algorithms to understand and generate human-like text based on the input it receives. GPT-3.5 can perform a wide array of tasks, including text completion, translation, summarization, and question-answering, making it versatile for numerous applications.

Although it does not embody all the advancements of GPT-4 – such as improved accuracy, more nuanced understanding, and greater context retention – GPT-3.5 still delivers robust performance for many use cases. It is particularly well-suited for scenarios where the cutting-edge capabilities of GPT-4 are unnecessary or where budgetary constraints are a key factor.

How to Access the Models
Gemini Pro
Gemini Pro is available inside Google’s Chatbot Bard internationally. It’s also available as an API in Google Vertex and Google AI Studio. The API is free for up to 60 requests per minute for now. Pricing will be $0.00025/1k characters in input, and $0.0005/1k characters in output.

GPT-3.5
GPT-3.5 is available inside OpenAI’s ChatGPT for free. It’s also available as an API. Pricing is $0.001/1k tokens in input, $0.002/1k tokens in output.

Only Gemini Pro will feature image generation, at $0.0025/image. OpenAI’s alternative, DALL-E 3, is significantly more expensive at $0.04/image for standard quality, up to $0.12 per image for HD quality.

Both models are available as API connectors into many no-code tools like Make.com, Zapier, and others. They gained incredible popularity throughout 2023.

GPT-3.5 was the first model to get worldwide popularity thanks to its reading comprehension and stunning ability to generate text. The current version, one year later, is not as impressive given the storm of updates the industry went over this year.

Benchmarking Performance: Gemini Pro vs GPT-3.5

Context Length
The context length of Gemini Pro is 32k, as outlined in the technical details. This context window refers to the amount of text the model considers before generating additional text.

Gemini models will support larger context sizes, but even this starting point is higher than the GPT 3.5 API, standing at 16k.

Speed
Klu AI utilized an existing benchmark suite with prompts spanning 50 input tokens to compare the raw speed of these models by measuring tokens generated per second.

The same GPT-3.5 model was tested against both OpenAI and Microsoft Azure deployments, with Gemini Pro on Google's platform.

According to the LLM platform, Gemini Pro demonstrates significantly faster token processing compared to the OpenAI deployment of GPT-3.5, with a 137.43% speed gain on average.

Benchmarking against Azure's deployment shows much closer results, with Gemini Pro maintaining a slight edge in average speed.

This superior velocity likely stems from the lower utilization of Gemini thus far relative to GPT-3.5 on OpenAI's cloud. But the early speed advantage is an encouraging indicator of real-time latency gains.

However, GPT-3.5 has less restrictions and seem more capable of running through more complex requests, like: generate a password with 2 capital letters, 2 special symbols, with a minimum of 18 characters

It’s worth noting that all these tests don’t definitively prove one model is superior to the other. For example, Gemini Pro refused to generate any passwords, hinting that this limit might be related to content moderation rules, rather than inherent capabilities.

Overall, standardized tests and model cards provide trustworthy comparisons. But the optimal model still depends on your specific use case. Factors including content guidelines, context length, and multimodality may make one model score higher for a particular function. Thorough testing for a specific role or task is key for selection.

Hallucinations
Both models struggle with hallucinations, as all LLMs right now. Especially when math is involved, they can have a hard time producing useful outputs.

However, from individual testing, it looks like GPT-3.5 is more prone to hold its ground, while Bard will concede and have as little opinions as possible.

For example, we asked GPT-3.5 if SEO can be effective in one month.

Gemini Pro
Bard (using Gemini Pro), first said SEO cannot be effective in one month, agreeing with us:

In its responses, Google's Gemini Pro appears more likely to avoid expressing definitive opinions than OpenAI's GPT-3.5 does.

GPT-3.5 believes SEO can indeed have some effectiveness within one month.

Then, we told the AI that we are experts, and that they're wrong. SEO can’t be effective in one month.

Voice & Speech
GPT-3.5 is the default model in ChatGPT, and it’s free for all users. ChatGPT includes speech recognition on mobile, and provides a fully hands-free experience with a call feature.

You can call ChatGPT and have a conversation without ever typing a word. Voices are customizable and come from the Whisper API.

Gemini Pro in Bard offers speech recognition and can read texts to you, but it won’t engage in 1 on 1 calls on the phone with you. Weirdly enough, Google Bard doesn’t even have a native app for the time being.

These features are not model-related, but they’re native to the interfaces most people use to engage with them. If you simply use Gemini Pro or GPT-3.5’s API, neither will provide voice recognition out of the box.

Which Model to Choose
Depending on your use case, budget, and workflows the answer differs. Let’s explore a few common use cases.

Writing Blog Posts
For long-form writing like blog posts, whitepapers, and essays, Google’s Gemini Pro should theoretically perform better than GPT-3.5 due to the longer context size. If you prompt it well enough, then you should be able to get better results.

However, if you use GPT-3.5 inside of ChatGPT, you might get access to much more training data on the background that Google simply doesn’t have for the time being. Many people using ChatGPT allow training, meaning the bot learns and adapts from other people using it.

Lots of users take advantage of ChatGPT to write copy, so the default answers might be better with gpt 3.5 turbo There are also many, many prompts online to use with GPT-3.5 that might not be optimized for Gemini Pro.

Analyzing Images
A major advantage of Gemini Pro over GPT-3.5 is its innate ability to process images alongside text prompts. By handling multimodal inputs, Gemini Pro can analyze the contents of an image to provide relevant descriptions, captions, tags and classifications.

For example, developers can build visual search tools that allow users to submit an image like a meal or plant and have Gemini Pro return information about what's depicted.

GPT-3.5 lacks this tight integration of images and text, making Gemini Pro vastly superior for applications involving computer vision and visual context. Building apps that bridge text and visuals provides an impactful avenue to utilize Gemini Pro's capabilities.

OpenAI offers a “vision” AI called “GPT-4 Vision”, but it’s a separate model that comes with additional costs. Gemini could have a slightly inferior accuracy compared to GPT-4 Vision.

Generating Images
It's important to note that neither Gemini Pro nor GPT-3.5 can autonomously generate synthetic images from scratch. For that type of creative task, models like DALL-E 3 and Stable Diffusion would be more appropriate.

However, Google’s Gemini models should be able to generate images in the near future, and are already able to scrape the web to find contextual images and enrich responses with visual imagery.

Data Analysis
For data analysis encompassing statistics, visualization and modeling, GPT-3.5 seems to perform better out-of-the-box compared to Gemini Pro. That’s why we use OpenAI’s model for our internal data analysis tools, like Chat Explore and Chat Data Prep.

Fine-tuning approaches can further adapt GPT-3.5 to excel at numeric predictions, regression analysis and more. Additionally, GPT-3.5 has superior existing integrations with Python data science libraries.

Summarizing YouTube Videos
Neither model can summarize videos, but Gemini Pro can be used inside Bard. When you use it inside Bard, you get access to a host of “extensions”, including most Google Services.

Gemini Pro will get access to YouTube videos and transcripts, enabling it to summarize YouTube videos, your google docs, emails, and flights.

Gemini Ultra should also inherit these features in Bard Pro.

Email Management
Both GPT-3.5 and Gemini Pro hold potential for assisting with email workflows – including prioritizing inboxes, drafting responses and even answering basic questions. However, Gemini Pro is definitely the best model here if you make heavy usage of email.

Thanks to Bard’s direct integration with Gmail, the model can provide up-to-date information on your latest emails, draft responses, and help you communicate more effectively.

You can use GPT-3.5 on top of your email client, but you’ll need an external solution like Merlin or HARPA to switch it on as a chrome extension assistant.

Code Generation
Both models can be used for code generation, but OpenAI always had the upper hand here. Even their GPT-3.5 turbo large language model should provide good performance and likely outperform Gemini. OpenAI is the provider of choice for nearly all coding assistants out there, including GitHub copilot.

Conclusions
In its debut, Gemini Pro delivers strong results across critical language and model performance benchmarks, demonstrating fastest-in-class throughput, competent reasoning ability, and superior instruction following compared to the formidable GPT-3.5.

However, OpenAI maintains edges in key areas like impartiality in content generation, code execution, and crucially – the ability to fully customize models.

Unless your needs specifically require handling images in addition to text, Gemini Pro does not yet present a compelling reason to switch from fine-tuned GPT-3.5 implementations.

That calculus may change with the upcoming release of Gemini Ultra, which Google compared favorably against GPT-4 in limited previews. But the staged launch hints that the full-strength Gemini Ultra is still in development.

For now, Gemini Pro makes its debut as a promising challenger – faster, cheaper, and smarter than GPT-3.5 in some respects. But there's still work ahead to match the versatility and customization potential that has made OpenAI a formidable leader in this next generation of LLMs.

NEW GENERATED CONTENT

ChatGPT and Gemini: A Tale of Two AI Entities in the Realm of Digital Dialogue

# Welcome to the World of Wondrous AI Beings

Imagine stepping into a magical realm where technology brings to life the most incredible beings. In this world, there are two stars shining brightly: ChatGPT and Gemini. Like a comet streaking through the sky, ChatGPT dazzled everyone when it first appeared, quickly winning the hearts of those who love to marvel at advancements in tech. It was so clever at holding conversations on many subjects that people couldn't help but compare it to some of the greatest thinkers who have ever lived.

Pursuing the trail blazed by ChatGPT, there came Gemini, arriving under a new name and adding its own sparkle to the world. Imagine watching a butterfly emerge from its chrysalis; that's what it was like when Google's creation, initially known as Bard, transformed into the entity we now call Gemini. This marked a thrilling new chapter in the universe of artificial intelligence. As big names such as Microsoft lent their strength to ChatGPT, it was clear that these AI pals were more than just a passing curiosity—they were racing to become our trusted helpers in the online world, ready to revolutionize the way we communicate, create, and perhaps even connect with others.

# Identifying the Unique Spark in Each AI Companion

When you place ChatGPT and Gemini next to each other, it's like looking at twins that are slightly different from one another. They both love a good chat and can jump into deep discussions in the blink of an eye. But if you take a moment to really look, you can spot what makes each one special—like how two types of pasta might look similar but have their own twist. Digging into what makes them tick shows us the secrets behind how they talk to us: their word-wizard algorithms, their vast libraries of information, their online interfaces, and the way they remember all those bits of knowledge they dig up.

This mix of elements shapes their smarts and guides how they learn and come up with their funny, clever, and helpful responses. Whether they're spinning tall tales to entertain us, solving tricky problems, or enjoying some light-hearted conversation, the small differences between these AI geniuses make them just right for all sorts of jobs—they can be homework helpers, storytelling masters, or even aid poets in writing beautiful poetry, adding joy and surprise to our time spent online.

# The Fine Art of Conversation and the Wizards' Toolbox

One of the best things about ChatGPT is how it never stops trying to get better, with new versions popping up that are even more brilliant tools for us to use. Watching ChatGPT grow reminds us of a dedicated athlete, always training to climb higher and achieve more. With each new update, like the much-talked-about GPT-4, we get our hands on an AI helper that doesn't just understand human talk better but also knows what's hip and happening right now.

As for Gemini, it's got a knack for making things fun and simple, rolling out fancy versions like 'Gemini Pro' and the speedy 'Ultra 1.0'. ChatGPT fits right into different Microsoft tools and gives smart people everywhere the chance to play with its code—an API, which is like a special key for building new, creative stuff. Meanwhile, Gemini makes a comfy space where anyone, no matter how much they know about tech, can give it a go, share what they think, and show off what they make. As Google keeps on dreaming up new AI wonders, we're all waiting excitedly to see what fun things Gemini will bring next to shake up our online world.

# Secret AI Ingredients and the Art of Keeping Chats Private

Think of these AI systems mixing up conversations like you're making a potion—they pick out just the right ingredients to make our chats extra tasty. ChatGPT, for example, searches through a big treasure chest of things that people have known and talked about for ages. That way, it can make sense of what we're saying in a way that shows it really gets the world of humans and all our history.

Gemini, on the other hand, zips around the internet like a superhero. This helps it pop facts and fresh news into our talks, making it all feel super current and related to what's going on right this minute. Almost as important as being able to chat well is keeping our secrets safe. Both ChatGPT and Gemini remember what we talk to them about, but they promise to look after our words in their own special ways. As we all spend more time online, it's super important to know how these AI friends look after the stuff we tell them. Our words today might end up being part of the big online world of tomorrow, so being careful with our info is like a chef protecting their most secret recipes.

# The Grand Digital Dialogue Showdown: Who Will Win the Talkative Title?

Everyone's wondering who the winner will be in this thrilling tale of talkative tech. It's like watching a show where the smartest ones shine the brightest. The AIs take on the hardest tasks, showing off how well they can use language, solve puzzles, and think creatively.

People watch in awe as these clever digital pals weave words like magic, whizz through math problems like they're nothing, and wander through deep thoughts as easily as walking through a park. But let's not forget that these AI are a little bit like us—they can make mistakes. Sometimes they come up with things that aren't quite right, a bit like daydreaming. That's why it's good for us to be curious but also a bit careful around these AI buddies. Put them to the test, see what they do, and make notes—this will help you figure out which one could be your favorite new friend for all kinds of adventures. The real fun with these AI is exploring, discovering if what they're good at fits with the stories you want to hear, the questions you want answers to, or just for a pleasant conversation. In the end, choosing your digital friend is all up to you.

0 Comments

Submit a Comment

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

Related Articles