Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by js4ever on Thursday November 19, 2026 @07:27PM
(#50568564)
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)
[ Parent
| on HN ]
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by copperx on Thursday November 19, 2026 @07:30PM
(#50568581)
[delayed]
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by mjburgess on Thursday November 19, 2026 @07:30PM
(#50568590)
And tokens/task is very high. They don't seem to have figured out making the models usable in a typical interactive workflow, ie., they're in a Opus-4.7 era.
Very high hallucination rates too.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by applicative on Thursday November 19, 2026 @08:47PM
(#50569141)
[delayed]
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by SwellJoe on Thursday November 19, 2026 @07:31PM
(#50568596)
I think it's just you. Carbon is excellent but extremely slow. If Neon is better than or equal to Carbon while also being a lot faster, that'd be a great model. I haven't tried Neon, yet, but they seem to have understood the assignment with the latest round of models.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by vickychijwani on Saturday November 21, 2026 @08:55PM
(#50595473)
Neon is exactly that. Carbon was unusable, Neon has been excellent so far.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by azan_ on Thursday November 19, 2026 @07:32PM
(#50568602)
Yes. Every Google model so far has been disappointment. And their biggest moat, the integration into other google products has been laughable. Today I've asked gemini in gmail to download all attachments from one e-mail address and it turned out it's unable to do it. It's unbelievable how incompetent they are, Google has such a massive edge over OAI and Anthropic and it's still losing.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by andunieee on Thursday November 19, 2026 @07:42PM
(#50568676)
You mean they are not providing you with their best models for free?
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by azan_ on Thursday November 19, 2026 @08:11PM
(#50568903)
No, why would you think that? I'm paying customer.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by drivebyhooting on Thursday November 19, 2026 @10:40PM
(#50569858)
Codex can do all the Gmail integration I’ve needed.
Where Gemini shines for me is programmatically accessing YouTube content (engineering channels) and leveraging that.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by hadlock on Thursday November 19, 2026 @07:34PM
(#50568616)
After hearing some good things from my tokenmaxxing buddies (or whatever you want to call them, AI enthusiasts), I got a $20/mo sub to try out Neon and it's just breezed through some hardware graphics bring-up problems I've been struggling with on Sol/Astra and Fable. I'm gonna drop my $200 OpenAI sub this coming month in favor of Google's $200 plan just for more Neon tokens.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by WaltPurvis on Thursday November 19, 2026 @08:29PM
(#50569017)
Interesting. I've been considering switching my OpenAI sub for Google also. I think a lot of the variance in results has to do with what programming languages you're using and what type of projects you're doing, but for me, on Swift/SwiftUI work, I've done exact head-to-head comparisons of OpenAI models and Opus 5.5, and Opus is so much better, so consistently, that I'm really wondering why I bother paying OpenAI $100/month. I use ChatGPT for some ancillary projects and personal stuff, but I don't even come close to using 100% of my plan. I might give Google a try.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by hirvi74 on Thursday November 19, 2026 @09:29PM
(#50569433)
> I've done exact head-to-head comparisons of OpenAI models and Opus 5.5, and Opus is so much better
I am just curious if you have always noticed this trend? I swear, a year ago or so, I was having the complete opposite experience, but something changed in the 3-6 months. I cannot comment on Swift UI, but Swift experiences have been the nearly identical. I felt like GPT used to be so much better with Swift (and C#) than Opus.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by WaltPurvis on Thursday November 19, 2026 @09:52PM
(#50569574)
I can't speak to the historical trend because I've only been doing substantial SwiftUI work with these models for about three months. But in my head-to-head comparisons, it's not strictly code where Opus has been better. Codex has made some very questionable choices in app architecture, etc., which I don't see from Opus.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by Yahivin on Thursday November 19, 2026 @07:37PM
(#50568641)
With Neon Gemini is good now.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by kridsdale1 on Thursday November 19, 2026 @09:38PM
(#50569497)
Neon Gemini Evangelion
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by asadm on Thursday November 19, 2026 @07:43PM
(#50568689)
this week I ran out of codex astra quota and switched to antigravity, boy is Gemini Carbon amazing model! It actually helped achieve a breakthrough I was stuck on for weeks with Astra.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by danpalmer on Thursday November 19, 2026 @07:48PM
(#50568732)
It's just you. Since Argon, the Gemini models have been producing good results for me side-by-side with Opus/Fable models on the same prompts. Not always winning, but increasingly so with Carbon/Neon.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by etoxin on Thursday November 19, 2026 @07:49PM
(#50568743)
I'm using AI heavily at work. I'm switching all my opus 5.5 sub-agents to neon. I'm quite impressed.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by horacemorace on Thursday November 19, 2026 @07:59PM
(#50568810)
Carbon changed my mind.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by CamperBob2 on Thursday November 19, 2026 @08:11PM
(#50568899)
Is it just me or all Google models are terribly bad?
Not this one.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by elxr on Thursday November 19, 2026 @08:24PM
(#50568979)
Argon was bad yeah.
All the 3.x flash models were actually dumb compared to everything else it competed with.
Neon seems promising.
Re:Gemini 4 Neon is the new #1 on the Models Engineering Index
by _s_a_m_ on Thursday November 19, 2026 @09:07PM
(#50569278)
i already went through the whole quota for Neon, it is on high to xhigh almost as good as Opus 5.5, almost equal. Most people who dont do deep learning model rewrites and other math stuff and statistics like me wont probably even notice a difference.