| ▲ | Gemini 4 Neon is the new #1 on the Models Engineering Index(git-aarvin.github.io) | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| 57 points by hn-aarvin 2 hours ago | 28 comments | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ▲ | postalcoder 13 minutes ago | parent | next [-] | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
I don’t think anybody who has 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 claude/agents/gemini.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 leaving scars of the previous verbiage behind. Art-wise, it’s more capable, in my experience, than Fable. There are some pieces of art that I’ve struggled to iterate with using fable that Neon handled with ease. 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. 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. | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ▲ | largbae 23 minutes ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
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 | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ▲ | johnmlussier 2 minutes ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Can’t use it for anything defensive audit oriented. Refuses too often. Google seemingly not trying at all on the CVP or Daybreak front. | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ▲ | YuechenLi 39 minutes ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
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. | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ▲ | dw_arthur 8 minutes ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
I prefer to use agents from the command line. Does Antigravity CLI deliver a good experience? | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ▲ | zf00002 21 minutes ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
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. | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ▲ | andunieee 32 minutes ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
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? | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ▲ | _s_a_m_ 3 minutes ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
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). | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ▲ | quantisan an hour ago | parent | prev | next [-] | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
When and why should I trust this index over others? | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ▲ | js4ever an hour ago | parent | prev [-] | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
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) | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||