Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Gemini 3 Pro Model Card [pdf]

storage.googleapis.com

Post reply on HN
Print view View original

111–120 of 359 posts

Re: Gemini 3 Pro Model Card [pdf]

#111

Post by Fornax96 »

zozbot234 wrote: post #94
Fornax96 wrote: post #50

Earlier quoted context omitted.

Creator of pixeldrain here. I have no idea why my site is blocked in Spain, but it's a long running issue. I actually never discovered who was responsible for the blockade, until I read this comment. I'm going to look into Allot and send them an email. EDIT: Also, your DNS provider is censoring (and probably monitoring) your internet traffic. I would switch to a different provider.

Could it be that some site in your network neighborhood was illegally streaming soccer matches?

I have my own dedicated IP range. And they specifically blocked my domain name, not the addresses. I don't know what the reason is. I have been trying to find out since the start of this year.

Re: Gemini 3 Pro Model Card [pdf]

#112

Post by HereBePandas »

Palmik wrote: post #96
mynti wrote: post #75

It is interesting that the Gemini 3 beats every other model on these benchmarks, mostly by a wide margin, but not on SWE Bench. Sonnet is still king here and all three look to be basically on the same level. Kind of wild to see them hit such a wall when it comes to agentic coding

Also does not beat GPT-5.1 Codex on terminal bench (57.8% vs 54.2%): https://www.tbench.ai/ I did not bother verifying the other claims.

Not apples-to-apples. "Codex CLI (GPT-5.1-Codex)", which the site refers to, adds a specific agentic harness, whereas the Gemini 3 Pro seems to be on a standard eval harness.

It would be interesting to see the apples-to-apples figure, i.e. with Google's best harness alongside Codex CLI.

Re: Gemini 3 Pro Model Card [pdf]

#113

Post by basch »

gizmodo59 wrote: post #30
remus wrote: post #27

Earlier quoted context omitted.

I think google is uniquely well placed to make a profitable business out of AI: They make their own TPUs so don't have to pay ridiculous amounts of money to Nvidia, they have a great depth of talent in building models, they've got loads of data they can use for training and they've got a huge existing customer base who can buy their AI offerings. I don't think any other company has all these ingredients.

While I don’t disagree that Google is the company you can’t bet against when it comes to AI, saying other companies are done is a stretch. If they have a significant moat then they should be at the top all the time by then which is not the case though.

ChatGPT's moat is their name and user habit. People who are using it will keep using it. All/most of the products are _good enough_ for the people who already got used to using them, that they arent exploring competitors.

Microsoft has the chance of changing habit the most by virtue of being bundled into business contracts that have companies with policies not allowing any other product in the workplace.

Re: Gemini 3 Pro Model Card [pdf]

#114

Post by danielbln »

fariszr wrote: post #110
scrlk wrote: post #23

Benchmarks from page 4 of the model card: | Benchmark | 3 Pro | 2.5 Pro | Sonnet 4.5 | GPT-5.1 | |-----------------------|-----------|---------|------------|-----------| | Humanity's Last Exam | 37.5% | 21.6% | 13.7% | 26.5% | | ARC-AGI-2 | 31.1% | 4.9% | 13.6% | 17.6% | | GPQA Diamond | 91.9% | 86.4% | 83.4% | 88.1% | | AIME 2025 | | | | | | (no tools) | 95.0% | 88.0% | 87.0% | 94.0% | | (code execution) | 100% | -…

This is a big jump in most benchmarks.And if it can match other models in coding while having that Google TPM inference speed and the actually native 1m context window, it's going to be a big hit. I hope it's isn't such a sycophant like the current gemini 2.5 models, it makes me doubt its output, which is maybe a good thing now that I think about it.

> it's over for the other labs.

What's with the hyperbole? It'll tighten the screws, but saying that it's "over for the other labs' might be a tad premature.

Re: Gemini 3 Pro Model Card [pdf]

#115

Post by floppyd »

jll29 wrote: post #52

[flagged]

Gemma is an open-weight version of Gemini and obviously much less capable probably even than 2.5 Flash. Also the story you are linking to is a complete nothing burger, models are still very much hallucinating, especially on some extremely niche topics, I don't see how another politician trying to capitalize on that is attention-worthy at all.

Re: Gemini 3 Pro Model Card [pdf]

#116

Post by FrequentLurker »

basch wrote: post #98
Alifatisk wrote: post #71

Earlier quoted context omitted.

These numbers are impressive, at least to say. It looks like Google has produced a beast that will raise the bar even higher. What's even more impressive is how Google came into this game late and went from producing a few flops to being the leader at this (actually, they already achieved the title with 2.5 Pro). What makes me even more curious is the following > Model dependencies: This model is not a modification o…

At least at the moment, coming in late seems to matter little. Anyone with money can trivially catch up to a state of the art model from six months ago. And as others have said, late is really a function of spigot, guardrails, branding, and ux, as much as it is being a laggard under the hood.

> Anyone with money can trivially catch up to a state of the art model from six months ago.

How come apple is struggling then?

Re: Gemini 3 Pro Model Card [pdf]

#117

Post by felipeerias »

mynti wrote: post #75

It is interesting that the Gemini 3 beats every other model on these benchmarks, mostly by a wide margin, but not on SWE Bench. Sonnet is still king here and all three look to be basically on the same level. Kind of wild to see them hit such a wall when it comes to agentic coding

IMHO coding use cases are much more constrained by tooling than by raw model capabilities at the moment. Perhaps we have finally reached the time of diminishing returns and that will remain the case going forward.

Re: Gemini 3 Pro Model Card [pdf]

#118

Post by this_user »

Yossarrian22 wrote: post #103
jstummbillig wrote: post #58

Earlier quoted context omitted.

Does not get old.

It’s not just irritating, it’s repetitive

I'm sorry, you are absolutely right.

---

But seriously, I find it helps to set a custom system prompt that tells Gemini to be less sycophantic and to be more succinct and professional while also leaving out those extended lectures it likes to give.

Re: Gemini 3 Pro Model Card [pdf]

#119

Post by zed31726 »

jmkni wrote: post #69
denysvitali wrote: post #59

Title of the document is "[Gemini 3 Pro] External Model Card - November 18, 2025 - v2", in case you needed further confirmation that the model will be released today. Also interesting to know that Google Antigravity (antigravity.google / https://github.com/Google-Antigravity ?) leaked. I remember seeing this subdomain recently. Probably Gemini 3 related as well. Org was created on 2025-11-04T19:28:13Z ( https://api.g…

what is Google Antigravity?

My guess is based on a gif tweeted by the ex CEO of windsurf who left to join Google of a floating laptop: it'll be a cursor/windsurf alternative?

Re: Gemini 3 Pro Model Card [pdf]

#120

Post by dgacmu »

postalcoder wrote: post #79
Alifatisk wrote: post #71

Earlier quoted context omitted.

These numbers are impressive, at least to say. It looks like Google has produced a beast that will raise the bar even higher. What's even more impressive is how Google came into this game late and went from producing a few flops to being the leader at this (actually, they already achieved the title with 2.5 Pro). What makes me even more curious is the following > Model dependencies: This model is not a modification o…

Google was never really late. Where people perceived Google to have dropped the ball was in its productization of AI. The Google's Bard branding stumble was so (hilariously) bad that it threw a lot of people off the scent. My hunch is that, aside from "safety" reasons, the Google Books lawsuit left some copyright wounds that Google did not want to reopen.

The memory of Microsoft's Tay fiasco was strong around the time the brain team started playing with chatbots.
Post reply on HN