logoalt Hacker News

Gemini 4 Neon is the new #1 on the Models Engineering Index

271 points • by hn-aarvin • yesterday at 11:35 PM • 163 comments • view on HN

Comments

postalcoder • today at 1:00 AM

I don’t think anyone who have yet commented has used the actual model. But, to be fair to the commenters, google has made it very hard for them to do so without spending a ton of money.

Neon is a really good model. It’s currently my favorite model to use. Coding-wise, it’s equivalent to Opus 5.5/Fable. Documentation-wise, it is great. If you have access to Neon have it take a crack at simplifying your agents.md. It’s the first model I’ve run that criticized the amount of ceremony in my instructions and suggested solid simplifications. It also makes clean edits to documents without leaving scars of the previous verbiage behind.

Art-wise, it’s more capable, in my experience, than Fable. I’ve been using fable/opus heavily to make art assets for my application (I shared in a previous comment that procedural art has completely obviated gpt-image art for me) and I’ve started to run into a wall with how far I could iterate with fable. I had neon take a crack at the assets I struggled to improve and it did a grand job.

In terms of working together with a model and how it communicates to you, I love this model. The model knows how to clearly communicate to you. It is such a breath of fresh air over Opus and Fable which, despite the improvements, I feel is actively trying to damage my brain with its unnatural prose. It's hard to describe how it feels to have a model that you feel respects your time and energy with proper writing, and the subsequent delight that arises from the feeling of wanting to engage in smaller details again.

Neon has a big model smell, but the miracle and irony is it’s supposedly based on a smaller base model than Carbon. On google’s model page, they previously wrote that Neon shares the same base model as Hydrogen! It is thought that Argon and Carbon share the same base model.

My impressions will probably change as I use this for longer than a day, but my initial impression is: I don’t know how google pulled this off.

➕ show 11 replies
largbae • today at 12:51 AM

Neon is a contender. Neon "high" appears faster and cheaper than Opus 5.5 "medium" with similar results on long-running language porting work in a large monorepo.

The speed is the biggest win IMO. When Carbon came out, I tried to give it a shot, but it was so slow that I went back to Opus just for productivity, nevermind quality. Today I started Neon on one worktree and Opus on another, and Neon did so well that I have now switched for both.

Code quality looks great. Comment-wise it has its own Claudese(exclamations like "this function has a concurrency bug and it's a sharp one!"), but overall I like reading it more than Opus. Might just be because I am not yet tired of its quirks though.

Oh, after a productive day on this particular work I had only spent $30 of Neon vs. $70 of Opus yesterday. YMMV

➕ show 3 replies
dowakin • today at 2:32 AM

Fully agree. Neon is my main model right now. I have a pretty advanced setup with multiple agents, coordinators, etc. It's basically a "factory" customized for me. It ran on Claude for a long time, then on Codex for the past three months, and now it runs on Google models. Neon is good, predictable, and smarter than me :)

Agy has a bunch of good slash commands for different use cases. And the biggest thing for me is that it doesn't annoy me with security refusals. It helped me with my garage door, for example, when another model refused.

gregwebs • today at 1:43 AM

If you watch Youtube much at all, Youtube Premium Lite (no ads) is well worth the $9/month. This is included with their $20/month AI plan. Spending that other $11/month wasn't worth it before Neon, but it might be now.

There are 3 different antigravity quotas:

* gemini (previously just Gemini 3.8 Flash)

* claude and gpt (very small quota)

* argon (very small quota)

The Gemini quota now includes Neon and Hydrogen. Hydrogen (medium) competes with DeepSeek (high). Its within 2x on cost and more intelligent.

This is all from benchmarks- I am only just trying these models out now.

➕ show 3 replies
rspeele • today at 3:36 AM

I have a little WIP game (don't we all...) and I use models through MCP to author maps for the game. It's 3d-ish. Neon just did a really nice job authoring a map section on a hillside. It did indeed seem about equivalent, subjectively, to Opus. This is impressive because GPT models, including the just-released 6.2 Astra, need extra guidance to do a convincing job at authoring my maps within their constraints. Without special prompts, GPT will build indoor spaces with sloping floors that follow the hillside they're built on. It will judge its own work as great when it looks objectively ugly and repetitive. Etc.

Opus does a fantastic job without handholding, and in an early sample it looks like Neon does too. But I've only tested one tile because I hit my 5hr limit. I'm "only" on the $20/mo plan for Google.

➕ show 1 reply
YuechenLi • today at 12:34 AM

Ok, so I can see that this is a benchmark the submitter made and submitted themselves, which is kinda misleading and should at least be disclosed.

But my question is, what does this benchmark actually measure about the LLM's engineering abilities? It just looks like a page of random bar graphs to me.

➕ show 1 reply
seizethecheese • today at 4:15 AM

The bottom chart (looks like a spiderweb) looked weird, Neon looked like a stub, so I looked into it and only 3/8 of the benchmarks are populated for Neon, whereas 6/8 are for Fable.

Seems like the methodology here isn’t sound? Not sure why we’d care about this over something like Artifical Analysis index.

➕ show 1 reply
golfer • today at 3:49 AM

Neon performs well on popular benchmarks, but I found these lesser-known benchmarks interesting too. It's a very strong model.

Surge AI DAYJOB - Finance: https://x.com/HelloSurgeAI/status/2123561368473485314

Parallel Search Intelligence: https://x.com/p0/status/2123497882322141453

SlopCop: https://slopcop.com/power-ranking

Cognition: https://x.com/cognition/status/2123553121653944391

specked-citrus • today at 1:25 AM

This is not a real index. Gemini 4 Neon is only covered by 3 out of the 8 benchmarks included. This post is clickbait.

➕ show 2 replies
throwitaway222 • today at 4:12 AM

6.1 / 6.2 sol are still the sweet spot for me. 2 plus accounts and I'm rolling all day long.

hazmazlaz • today at 4:23 AM

I just had a pretty negative experience with Neon 4.

(Antigravity GUI client on MacOS, Extra effort level)

I asked agy to find bugs and performance optimization opportunities in some code implementing a OpenGL to Metal graphics bridge.

1. introduced four (4) P1 regressions, essentially breaking everything in a very obvious way

2. wrote no new tests for the code it wrote

3. its code failed five existing tests

4. at least half of the bugs it diagnosed were wrong, e.g. false finding entirely - not a bug, correctly working code

5. correctly diagnosed some previously undiscovered bugs, but either wrote partial or incorrect fixes for most of them

6. correctly diagnosed and wrote correct fixes for only 2 out of a total of like 10 "findings"

Disappointed, this sounded like it would be a big win for Google and put them back at the head of the pack.

ra • today at 3:57 AM

We have paid Gemini on our workspace plan and the models available are "Hydrogen" and 3.1 pro.

I really don't get Google's product strategy.

➕ show 1 reply
jstummbillig • today at 2:09 AM

Can someone speak to the sub options and real world allowance they bring, compared to those of of Ant and OpenAI for coding? Is it same-ish, is it very different?

alphax314 • today at 2:15 AM

It doesnt matter. If its not at least as efficient as opus 5.5… people want a good model that can be used for good. Astra was also good but would eat through the subscription in no time. The same for Fable 5. Opus 5.5 is the first model that made the subscriptions usable.

zf00002 • today at 12:52 AM

I've been impressed with my usage of Neon so far. Early impression at High and Extra is near enough to Opus 5.5 Extra for me. Usage has been pretty good for that effort level too.

johnmlussier • today at 1:11 AM

Can’t use it for anything defensive audit oriented. Refuses too often. Google seemingly not trying at all on the CVP or Daybreak front.

➕ show 1 reply
sva_ • today at 1:57 AM

Has anyone else run into the issue of all Gemini 4 models showing as "Unavailable" in agy with a Pro sub, despite working in the web chat? And if so, have you been able to resolve it?

lemax • today at 1:45 AM

Neon just feels so readable. I compared an analysis of a complex HVAC quote against Fable 5.2 and Neon and Neon gave back straightforward negotiating points, no straight-into-invented-jargon headings, and overall gave a response that felt reasonable and proportional to my questions. I’m not surprised that Google’s models can be good at such things, but it’s such a welcome change from these turgid AI responses that feel like wading through an ocean of Fable’s free associations.

zergrush • today at 2:32 AM

Google's comeback is just wild. So much for 'code red' at OpenAI, it's back to where it was when Gemini 2.5 pro released.

➕ show 1 reply
andunieee • today at 12:41 AM

How do I use it? Do I have to create a Google Console account and navigate through 15 menus in order to generate an API key? Or are there another 7 different ways to achieve similar outcomes?

➕ show 2 replies
noosphr • today at 2:19 AM

It can speak English. I don't really care about model capabilities when I don't have to actively get dumber interacting with the model.

DefineOutside • today at 2:49 AM

Gemini 4 Hydrogen is the first Google model that has lived up to its benchmarks for me. I'd rather use and trust Opus 5.5 more for planning, but Google's latest models seem fine for implementing, debugging issues, and code review. It's the one decent model that sits below Cursor's threshold for charging $0.25 more per million tokens for enterprise users. Neon would be as good at or better than Hydrogen, which is obvious from the naming scheme

RachelF • today at 2:17 AM

Maybe it's just me, but I'm struggling to keep up with these Google names, Hydrogen, Argon, Carbon, Neon, Flash, Flash-Lite and Pro.

quantisan • today at 12:23 AM

When and why should I trust this index over others?

➕ show 1 reply
forrestthewoods • today at 4:05 AM

These days I only trust vibes. And it takes about 2 to 4 weeks for vibes to settle.

Every single Gemini model that has come out strong has quickly failed the vibes.

hmokiguess • today at 2:07 AM

Marketing in HN is getting weird

➕ show 1 reply
mamcx • today at 3:15 AM

Work with opencode or pi?

➕ show 1 reply
dw_arthur • today at 1:06 AM

I prefer to use agents from the command line. Does Antigravity CLI deliver a good experience?

➕ show 3 replies
neutrinobro • today at 2:27 AM

I'm waiting for Gemini 92 Uranium.

topspin • today at 3:08 AM

Hmm. Based on this, I dropped a preliminary specification for an RF transceiver design into Neon. I've have a couple hours work into already with GPT-6.2 Sol/high.

This is really good. Worlds better, in fact. I'm impressed and delighted. Far better insights into power management and clocking. Component identification is awesome; far better than what I've been getting from Codex. It's like a friendly 30 year EEE just decided I'm worthy of as much help as I need.

10/10 will prompt again.

tremarley • today at 3:16 AM

Google models score great when ranked, but massively disappointing when used.

Let's see if this one lives up to it's ranking..

_s_a_m_ • today at 1:10 AM

I already used up the full quota for Neon. It is fine and close to Opus 5.5 on high to xhigh. At least the new quotas are much larger with the new models and you can get something done. I optimized multiple deep learning models and integrated them into an application pipeline and everything worked pretty much like Opus (almost).

wangguode • today at 1:16 AM

[flagged]

js4ever • today at 12:27 AM

Is it just me or all Google models are terribly bad? They all seems benchmaxed to hell and producing total crap compared to Claude or openai models from my own experience (mostly coding)

➕ show 13 replies