Megan Ellis / Android Authority

When it comes to choosing the best AI chatbot, the winner will depend on who you ask. Some people swear by Gemini and ChatGPT, but others prefer Claude. While I use both Gemini and Claude for everyday tasks, I prefer Claude for its high-quality responses and effectiveness for certain tasks, such as generating recipes.

That’s why I’m usually happy whenever I see Google take inspiration from Anthropic’s chatbot. However, a recent change to Gemini saw the AI tool adopt one of the most frustrating features of Claude — rather than learning from the many improvements it could make.

Gemini could learn a lot from Claude

Brady Snyder / Android Authority

In theory, Gemini should be the more proficient chatbot. It’s multimodal, meaning it can generate responses in a variety of formats, including images and videos. As a Google product, it also benefits from the company’s dominance in free apps and its status as the primary developer of Android. It also has unique features like Gemini Live, which allows you to hold audio conversations with the chatbot or use your phone’s camera to show it a live video feed and ask it questions about what you’re currently recording.

And yet, when it comes to anything mildly important, I turn to Claude instead. In my experience, Anthropic’s AI tool just delivers higher-quality responses. It also hallucinates a lot less.

For example, when I tried both AI tools for generating visuals of the next four weeks of Pokémon Go, Claude worked better overall. It made one mistake when it placed a date on the wrong day of the week (it said an event was on a Friday, even though the date was a Saturday). But at least the rest of the information was correct.

With Gemini, I asked it to generate an image of the events. On every attempt, it made significant mistakes. The first time around was the most accurate, though there were mistakes about when certain events ended. But every time since, when I asked it to generate a visual, it either completely makes up events or pulls events from last year. Pointing out the mistake doesn’t fix this either; it will just generate another made-up schedule. It eventually gives up and just sends a text list of events, which defeats the point of the entire exercise.

I frequently run into issues with Gemini hallucinations with other tasks, and the chatbot is often confidently incorrect. If you point out the error, it may argue back until it eventually admits its mistake. When I tested both chatbots for pulling data from a spreadsheet of my income for the year, Claude was the only one that arrived at the correct total. Gemini underestimated the total, but swore by its calculations.

Megan Ellis / Android Authority

Even though Claude is not multimodal, its interactive visuals give it a lot of functionality — including features that Gemini doesn’t have. For example, if you ask the chatbot to generate recipes, it creates an interactive card that you can use. This card also includes timers, and you can use it to switch the app to a focused cooking mode.

Other visual content includes sports scores and weather, as well as custom visuals. For example, you can get the chatbot to generate a calendar view of certain events (which is what I did with my Pokémon Go events prompt). It can also create custom charts and timelines.

Claude’s integrations still beat Gemini

Megan Ellis / Android Authority

Another thing that I’d hoped that Gemini would introduce is more integrations. As one of the biggest AI tools out there, I had expected more third-party apps to work with the chatbot. However, it’s still deeply embedded in the Google ecosystem, creating a bit of a walled garden. There’s pretty deep integration with tools like Gmail, Google Docs, and Google Keep. But I’ve moved away from Google apps in favor of tools that better suit me, so I don’t benefit very much from any of that.

When it comes to third-party integrations, currently, my Google Account allows me to integrate with Canva and Verify AI. But neither really interests me. Claude, on the other hand, supports plenty of third-party integrations, including on its free plan. These integrations also have nuanced permissions, unlike the blanket on/off toggle that Gemini requires when working with other services.

Gemini integrates mostly with Google apps, but Claude supports a wide variety of third-party app integrations.

For example, when I used Claude and Gemini to help me plan my day, Claude proved to be the better tool. Not only could I connect Claude to Asana with read-only permissions, but it also did a better job of accessing my shared Google Calendar events. Meanwhile, Gemini could only pull events from my main account’s calendar, which wasn’t helpful since I don’t use it for my work or meetings.

Claude’s mobile app also has a few tricks up its sleeve that Gemini doesn’t. I can create set reminders using Claude, and it adds them to my preferred tasks app. Gemini, however, only allows me to create these reminders with Google Tasks and Google Calendar.

Google decided to copy the worst part of Claude

Mitja Rutnik / Android Authority

As much as I’ve sung the AI’s praises, Claude has drawbacks. The most noticeable is its brutal limits in comparison to other AI tools. When I use Claude during peak hours, I easily use up my free five-hour limit within a few prompts. This means that I have to plan when I use the tool for important tasks.

Gemini has always had limits, but it recently drew inspiration from Anthropic and changed how it implements them. Specifically, Gemini changed from a prompt limit to a compute-based limit. It also introduced a five-hour limit, including for paid users.

The change resulted in users running into their limit within one or two prompts — a similar issue that occurred when Anthropic introduced its peak-time limits. Google did eventually fix issues causing limits to exhaust more quickly than they should, but the five-hour window remains.

It’s this five-hour window that annoys me the most, since it results in disjointed workflows. It’s the big reason I haven’t adopted Claude as my main chatbot. I never run into my weekly limit, but I frequently hit the five-hour limit.

The strict five-hour limits are the worst part of Claude, and something that Google has taken inspiration from.

With Gemini, the change feels even more disruptive. It technically has more generous limits than Claude, but you also have to take into account the mistakes that Gemini makes. Your limit isn’t used when the chatbot encounters an error — but when it generates incorrect content, it still counts. So those multiple incorrect Pokémon Go images I tried to generate pushed up my own limit to around 33%, even though I didn’t have a graphic I could actually use.

This limit also loomed over me when I was using Gemini Canvas. I was using the tool to create a mini app. However, the tool’s first output was a spreadsheet rather than an interactive web app. I then had to use a follow-up prompt to turn the output into something that was actually responsive.

To Google’s credit, at least it’s easy to check your limits, even if you’re on a free plan. You simply open Gemini, tap the hamburger menu to open the side menu, tap the settings cog, then tap “Usage limits.” I wish Claude would introduce something similar for free users. Currently, you can’t check your usage and are simply greeted by a pop-up once you’ve used your five-hour allocation.

Gemini’s new limits also feel less justified than those in Claude. While limits help manage demand, Google is a much larger company with significantly more resources than Anthropic. But there’s also the fact that Google is pushing Gemini into every service it can. Even Google Search is becoming increasingly generative and agentic.

At the same time, users can’t disable features such as AI Overviews (which do not count towards your account limits). AI Mode does count towards limits, and Google has pushed the tool through multiple shortcuts and UI flows. It also consistently prompts users to use its AI features in tools like Google Photos.

This strong AI focus and increasing monetization are why some people regret investing in the Google ecosystem. Personally, it reminds me that Google loves using certain features to eventually lure people into paid plans or higher subscription tiers once they’re hooked.

It’s a big reason why I haven’t leaned into the AI’s integrations with other Google tools. While I do use Gemini with my calendar, I haven’t connected it to services like Google Photos. Part of this was down to concerns over data privacy. At the same time, I also knew that a rug pull would eventually be on the way once Google found a way to monetize these features more effectively.