its newest LLM: Gemini 3. The mannequin is long-awaited and has been broadly 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 purpose of the article is to share my first impressions when utilizing Gemini 3, highlighting what works properly and what doesn’t work properly. I’ll spotlight my expertise utilizing Gemini 3 within the console and whereas coding with it.
Why it’s best to use Gemini 3
For my part, Gemini 2.5 professional was already one of the best conversational LLM accessible earlier than the discharge of Gemini 3. The one space I imagine one other LLM was higher at was Claude Sonnet 4.5 pondering, for coding.
The explanation I imagine Gemini 2.5 professional is one of the best non-coding LLM is because of its:
- Means to effectively discover the proper data
- Low quantity of hallucinations
- Its willingness to disagree with me
I imagine the final level is a very powerful. Some individuals need heat LLMs that really feel good to speak to; nonetheless, I’d argue you (as a problem-solver) all the time need the alternative:
You need an LLM that goes straight to the purpose and is keen to say that you’re improper
My expertise was that Gemini 2.5 was much better at this, in comparison with different LLMs reminiscent of 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 recent Gemini mannequin is thus very attention-grabbing, 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 might 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 sluggish in comparison with Gemini 2.5 Professional. Nonetheless, that is often not a difficulty, as I principally worth intelligence over pace, in fact, as much as a sure threshold. Although Gemini 3 Professional is slower, I positively wouldn’t say it’s too sluggish.
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 under:
I additionally observed it will generally generate photos, even when I didn’t explicitly immediate for it. The picture era within the Gemini console is surprisingly quick.
The second I used to be most impressed by Gemini 3’s capabilities was after I was analyzing the primary analysis paper on diffusion fashions, and I mentioned with Gemini to grasp the paper. The mannequin was, in fact, good at studying the paper, together with textual content, photos, and equations; nonetheless, that is additionally a functionality the opposite frontier fashions possess. I used to be most impressed after I was chatting with Gemini 3 about diffusion fashions, making an attempt to grasp them.
I made a false impression in regards to the paper, pondering we have been discussing conditional diffusion fashions, although we have been in truth 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 true intent behind my query, and considerably helped me deepen my understanding of diffusion fashions.
I additionally took a few of 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 often broader questions, although not notably tough ones.
The responses I obtained have been total 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 imagine Gemini 3 was higher at offering suggestions, and arising with extra artistic approaches to enhancing my writing.
Thus, to sum it up, Gemini 3 within the console is:
- A bit sluggish
- Sensible, and gives good explanations
- Good at uncovering issues I haven’t thought of, which is tremendous useful when coping with problem-solving
- Is keen to disagree with you, and assist name out ambiguities, traits I imagine are actually vital in an LLM assistant
Coding with Gemini 3
After working with Gemini 3 within the console, I began coding with it via Cursor. My total expertise is that it’s positively a superb mannequin, although I nonetheless favor Claude Sonnet 4.5 pondering as my important coding mannequin. The primary purpose for that is that Gemini 3 too usually comes up with extra advanced options and is a slower mannequin. Nonetheless, Gemini 3 is most positively a really succesful coding mannequin that may be higher for different coding use-cases than what I’m coping with. I’m principally coding infrastructure round AI brokers and CDK stacks.
I attempted Gemini 3 for coding in two important methods:
- Making the sport proven on this X publish, from only a screenshot of the sport
- Coding some agentic infrastructure
First, I tried to make the Sport from the X publish. On the primary immediate, the mannequin made a Pygame with all of the squares, however it 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 all the pieces. 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 needed to see Gemini 3 Professional’s potential to create a recreation from scratch.
After working the immediate above, it made a working recreation, the place the company are strolling round, I should purchase 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 total conclusion is that Gemini 3 Professional often will get the job accomplished, although I extra usually expertise bloated or worse code than I do when utilizing Claude 4.5 Sonnet. Moreover, Claude Sonnet 4.5 is sort of a bit sooner, 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 depends upon what you’re coding. In some conditions, pace is extra vital. Particularly types of coding, one other mannequin may be higher, and so forth, so it’s 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 may 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 referred to as Antigravity, although I haven’t tried it but.
Total impressions
My total impression of Gemini 3 is nice, and my up to date LLM utilization stack will appear to be this:
- Claude 4.5 Sonnet pondering for coding
- GPT-5 after I want fast solutions to easy questions (the GPT-app works properly to open with a shortcut).
- GPT-5 when producing photos
- 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, focus on software program structure, or related.
The pricing for Gemini 3 per million tokens appears to be like like the next (per November 19, 2025, from Gemini Developer API Docs)
- When you’ve got lower than 200k enter tokens:
- Enter tokens: 2 USD
- Output tokens: 12 USD
- When you’ve got 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
📩 Subscribe to my e-newsletter
🧑💻 Get in contact
✍️ Medium
You can too learn my different articles:
