its newest LLM: Gemini 3. The mannequin is long-awaited and has been extensively mentioned earlier than its launch. On this article, I’ll cowl my first expertise with the mannequin and the way it differs from different frontier LLMs.
The objective of the article is to share my first impressions when utilizing Gemini 3, highlighting what works effectively and what doesn’t work effectively. I’ll spotlight my expertise utilizing Gemini 3 within the console and whereas coding with it.
Why it is best to use Gemini 3
For my part, Gemini 2.5 professional was already one of the best conversational LLM obtainable earlier than the discharge of Gemini 3. The one space I consider one other LLM was higher at was Claude Sonnet 4.5 pondering, for coding.
The explanation I consider Gemini 2.5 professional is one of the best non-coding LLM is because of its:
- Capability to effectively discover the right info
- Low quantity of hallucinations
- Its willingness to disagree with me
I consider the final level is crucial. Some folks need heat LLMs that really feel good to speak to; nonetheless, I’d argue you (as a problem-solver) all the time need the other:
You need an LLM that goes straight to the purpose and is prepared to say that you’re incorrect
My expertise was that Gemini 2.5 was much better at this, in comparison with different LLMs resembling GPT-5, Grok 4, and Claude Sonnet 4.5.
Contemplating Google, in my view, already had one of the best LLM on the market, the discharge of a more moderen Gemini mannequin is thus very fascinating, and one thing I began testing proper after launch.
It’s price declaring that Google launched Gemini 3 Professional, however has not but launched a flash various, although it’s pure to assume such a mannequin shall be launched quickly.
I’m not endorsed by Google within the writing of this text.
Gemini 3 within the console
I first began testing Gemini 3 Professional within the console. The very first thing that struck me was that it was comparatively gradual in comparison with Gemini 2.5 Professional. Nonetheless, that is normally not a problem, as I largely worth intelligence over pace, in fact, as much as a sure threshold. Although Gemini 3 Professional is slower, I undoubtedly wouldn’t say it’s too gradual.
One other level I observed is that when explaining, Gemini 3 creates or utilises extra photographs in its explanations. For instance, when discussing EPC certificates with Gemini, the mannequin discovered the picture beneath:
I additionally observed it could generally generate photographs, even when I didn’t explicitly immediate for it. The picture technology within the Gemini console is surprisingly quick.
The second I used to be most impressed by Gemini 3’s capabilities was once I was analyzing the primary analysis paper on diffusion fashions, and I mentioned with Gemini to know the paper. The mannequin was, in fact, good at studying the paper, together with textual content, photographs, and equations; nonetheless, that is additionally a functionality the opposite frontier fashions possess. I used to be most impressed once I was chatting with Gemini 3 about diffusion fashions, making an attempt to know them.
I made a false impression in regards to the paper, pondering we have been discussing conditional diffusion fashions, although we have been in reality unconditional diffusion. Word that I used to be discussing this earlier than even understanding in regards to the phrases conditional and unconditional diffusion.
Gemini 3 then proceeded to name out that I used to be misunderstanding the ideas, effectively understanding the actual intent behind my query, and considerably helped me deepen my understanding of diffusion fashions.
I additionally took among the older queries I ran within the Gemini console with Gemini 2.5 Professional, and ran the very same queries once more, this time utilizing Gemini 3 Professional. They have been normally broader questions, although not significantly troublesome ones.
The responses I obtained have been general fairly related, although I did discover Gemini 3 was higher at telling me issues I didn’t know, or uncovering subjects / areas I (or Gemini 2.5 Professional) hadn’t thought of earlier than. I used to be, for instance, discussing how I write articles, and what I can do to enhance, the place I consider Gemini 3 was higher at offering suggestions, and developing with extra artistic approaches to bettering my writing.
Thus, to sum it up, Gemini 3 within the console is:
- A bit gradual
- Good, and supplies good explanations
- Good at uncovering issues I haven’t thought of, which is tremendous useful when coping with problem-solving
- Is prepared to disagree with you, and assist name out ambiguities, traits I consider are actually essential in an LLM assistant
Coding with Gemini 3
After working with Gemini 3 within the console, I began coding with it by way of Cursor. My general expertise is that it’s undoubtedly an excellent mannequin, although I nonetheless desire Claude Sonnet 4.5 pondering as my essential coding mannequin. The principle purpose for that is that Gemini 3 too typically comes up with extra advanced options and is a slower mannequin. Nonetheless, Gemini 3 is most undoubtedly a really succesful coding mannequin that is likely to be higher for different coding use-cases than what I’m coping with. I’m largely coding infrastructure round AI brokers and CDK stacks.
I attempted Gemini 3 for coding in two essential methods:
- Making the sport proven on this X submit, from only a screenshot of the sport
- Coding some agentic infrastructure
First, I tried to make the Recreation from the X submit. On the primary immediate, the mannequin made a Pygame with all of the squares, but it surely forgot so as to add all of the sprites (artwork), the bar on the left aspect, and so forth. Principally, it made a really minimalist model of the sport.
I then wrote a follow-up immediate with the next:
Make it look correctly like this recreation with the design and the whole lot. UseWord: When coding, you have to be far more particular in your directions than my immediate above. I used this immediate as a result of I used to be basically vibing within the recreation, and wished to see Gemini 3 Professional’s capacity to create a recreation from scratch.
After operating the immediate above, it made a working recreation, the place the friends are strolling round, I should buy pavements and completely different machines, and the sport basically works as anticipated. Very spectacular!
I continued coding with Gemini 3, however this time on a extra production-grade code base. My general conclusion is that Gemini 3 Professional normally will get the job finished, although I extra typically expertise bloated or worse code than I do when utilizing Claude 4.5 Sonnet. Moreover, Claude Sonnet 4.5 is kind of a bit quicker, making it the particular mannequin of alternative for me when coding. Nonetheless, I might in all probability regard Gemini 3 Professional because the second-best coding mannequin I’ve used.
I additionally assume that which coding mannequin is finest extremely is dependent upon what you’re coding. In some conditions, pace is extra essential. Particularly types of coding, one other mannequin is likely to be higher, and so forth, so it is best to actually check out the fashions your self and see what works finest for you. The worth of utilizing these fashions goes down quickly, and you’ll simply revert any modifications made, making it tremendous low cost to check out completely different fashions.
It’s additionally price mentioning that Google launched a brand new IDE known as Antigravity, although I haven’t tried it but.
General impressions
My general impression of Gemini 3 is sweet, and my up to date LLM utilization stack will seem like this:
- Claude 4.5 Sonnet pondering for coding
- GPT-5 once I want fast solutions to easy questions (the GPT-app works effectively to open with a shortcut).
- GPT-5 when producing photographs
- Once I need extra thorough solutions and have longer discussions with an LLM a few matter, I’ll use Gemini 3. Usually, to study new subjects, talk about software program structure, or related.
The pricing for Gemini 3 per million tokens seems like the next (per November 19, 2025, from Gemini Developer API Docs)
- If in case you have lower than 200k enter tokens:
- Enter tokens: 2 USD
- Output tokens: 12 USD
- If in case you have greater than 200k enter tokens:
- Enter tokens: 4 USD
- Output tokens: 18 USD
In conclusion, I’ve good first impressions from Gemini 3, and extremely suggest checking it out.
👉 Discover me on socials:
💻 My webinar on Imaginative and prescient Language Fashions
🧑💻 Get in contact
✍️ Medium
You may also learn my different articles:
