Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by quinndupont on Wednesday November 18, 2026 @08:09PM
(#50554735)
Fun analysis. I guess it’s not surprising to see the need for speed™ as an important factor, but who is using Fable for run of the mill coding work? It’s too pricey!
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by seizethecheese on Thursday November 19, 2026 @12:14AM
(#50556320)
Really happy to hear this. We're trying to build a leaderboard that reflects real work done by real people. Even the Arena systems are run in cloud containers.
Genuinely hoping some people sign up from this and use the app so we can get some more high quality data (it's open source: https://github.com/bottomless/agent-duel).
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by rootusrootus on Wednesday November 18, 2026 @08:15PM
(#50554778)
I guess what I really want to know is how Gemini 4 Neon w/Antigravity compares with Opus 5.5/Claude Code. I'm not really into using LLMs in a particularly advanced way, I just use CC like 99% of the time when I need to write something, and then maybe Codex to second guess it.
But that's about as complicated as I get. I have recently tried to use Copilot because that is what work wants us to use, and even with Opus 5.5 it is noticeably inferior to CC on the same model. Wild. So clearly the harness matters.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by seizethecheese on Wednesday November 18, 2026 @08:21PM
(#50554850)
Totally possible for your use case, though the analyses I’ve done on harness model interactions show it’s actually not that important for benchmark performance. https://micjm.com/blog/on-model-harness-interactions/
For what it’s worth, the linked article data (Agent Duel data) is all run on OpenCode. I’m curious if people would prefer we run each model in its native harness (at the expense of user experience because it’ll be buggy).
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by thefunnyman on Wednesday November 18, 2026 @08:23PM
(#50554870)
We had CC for a while and now have to use GHCP. As such I haven't used CC in like 6 months but around the time I switched I felt like GHCP CLI had pretty much caught up. Curious to hear what you feel are the gaps? Are you using the cli versions of both?
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by rootusrootus on Wednesday November 18, 2026 @08:56PM
(#50555124)
Yep, CLI versions for both GHCP and CC. To be honest, I haven't done enough actual coding with GHCP yet to get a feel, so my original comment may be too broad. But I've been repeatedly comparing and contrasting with CC for code reviews (as a team lead, I do more of that these days than coding). I have been pretty consistently getting about half again as many bugs from CC as from GHCP. And very nearly always correct, not hallucinations.
My company is slow-walking (and that is an understatement) our LLM usage, so the majority of work that I'm reviewing is human generated. After the stories I hear of what other people are experiencing when management is more enthusiastic, maybe I should count myself lucky.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by pritambarhate on Wednesday November 18, 2026 @08:26PM
(#50554903)
Also last I checked there was no clear flag to turn off training in paid plan of Antigravity. So if you care about that looks like Google doesn’t want you as their customer.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by riskassessment on Thursday November 19, 2026 @12:20AM
(#50556359)
I think you just turn off telemetry in antigravity to disable training. The Gemini app (including the web chatbot) is much more frustrating: the only way to disable training in the Gemini app (for a personal account) is to turn off apps and history.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by scottyah on Wednesday November 18, 2026 @08:33PM
(#50554971)
The models can be very optimized for the harness, Clem (of Hugging Face) just recently released a Qwen3.8 model that used RL training on the harness and it got some pretty significant gains in the benchmarks.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by rubyn00bie on Wednesday November 18, 2026 @09:53PM
(#50555471)
On a benchmark it might be minor or bullshit, but for me on real projects Claude Code has produced vastly better results than I was getting via Cursor or OpenCode. I used to believe the harness was negligible to having the agent do good work, but now I think it’s essential.
The big “aha” moment for me was seeing the wildly different results I’d get using something like Claude Design vs just prompting (even when using leaked system prompts). I then started hearing about the special harnesses available for biotech, science, and math that seem to be available for researches via OpenAI and Anthropic directly… which sort of further cemented in my brain how important it must be. I wish I got the same quality from Cursor, or OpenCode, as I do Claude but I just don’t.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by TacticalCoder on Wednesday November 18, 2026 @09:01PM
(#50555157)
Ah that's a new angle. After the "Google models are behind" and the "Google models are slower" and the "Google costs more per tokens", we're now at the following phase:
"OK, google models perform just as well, are faster and are cheaper but all that doesn't matter. Because the models, now that Google has very good ones, doesn't matter after all. All that matters is the harness".
And of course it's upvoted by the Anthropic shills.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by rootusrootus on Wednesday November 18, 2026 @11:21PM
(#50556055)
That's what you got from what I wrote?
I must not be deep enough into the conversation to get it. I was just sharing my own perspective. I don't follow AI development nearly as close as a lot of HN does. I don't hate it, but I don't love it either, it's just part of my job now.
> And of course it's upvoted by the Anthropic shills.
Gotta tell you, my post is barely above water ;-). It goes up, goes right back down, plenty of people seem to agree with you that I'm being mean to Google or something.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by retsibsi on Thursday November 19, 2026 @12:35AM
(#50556429)
> "OK, google models perform just as well, are faster and are cheaper but all that doesn't matter. Because the models, now that Google has very good ones, doesn't matter after all. All that matters is the harness".
Have they edited their comment since you replied? If not, this is one of the most egregious strawmen I've seen this week. You have brought a lot of your own baggage to this discussion, and stuffed it into a comment that said approximately none of what you claim to have taken from it.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by seizethecheese on Thursday November 19, 2026 @12:35AM
(#50556425)
> What makes something an "early vote"
In the battle, if side A finishes before side B we allow the user to vote for A before B finishes. (This is contrary to Arena.ai methodology, but I think it's the right thing for agents when sides can take a dramatically different amount of time.) This is why DeepSeek 4.1 Flash is doing so well in our leaderboard, it's super fast and often sufficient.
> and a "developer vote"
This is confusing, sorry. Inspecting our data it's almost entirely people doing software developments with agents. It's just a vote.
> (Also, out of curiosity, how are you funding this free inference for frontier models Is this not massively abuseable?)
This is a pivot from Bottomless (YC W19). That business is doing okay and funding our runway, in addition to fundraising back in 2021.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by fud101 on Wednesday November 18, 2026 @08:50PM
(#50555088)
I'm blown away by Neon, it's as good as Argon (which was amazing) but fast and cheap (i think). Opus is trash, Fable is trash - I will just use Opus for Day Job which it handles with ease and keep Neon for my serious side projects which Claude can't handle well at all.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by theturtletalks on Wednesday November 18, 2026 @09:01PM
(#50555163)
I’ll give it a spin on my software factory. The other Gemini models looked good initially and in benchmarks, but on long-running sessions and orchestration, it’s fallen short.
We’re reaching the point where certain models are really good at 1 thing. The person writing this blog post isn’t using Neon for large-scale orchestration, but I’m sure it excels in its usage. For me Fable 5.2 as the orchestrator and Opus 5.5 and grunt workers have led to the most robust software...so far.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by seizethecheese on Wednesday November 18, 2026 @09:08PM
(#50555197)
> The person writing this blog post isn’t using Neon for large-scale orchestration, but I’m sure it excels in its usage
I'm the person writing this. This is head to head battle data by real developers on top of OpenCode. The data is generated by an open source app so you can inspect it yourself (https://github.com/bottomless/agent-duel). The hitch is there's no real Neon data. This is purely projecting from Carbon's super slow but very good performance onto Neon's likely fast and likely equal performance.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by Implicated on Wednesday November 18, 2026 @10:47PM
(#50555841)
Dear god, as someone who has built a wildly robust "software factory" (mine doesn't stop at the output) - don't fork sessions. Just don't. Distill the relevant context into a new session, however you choose to do that.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by SimianSci on Wednesday November 18, 2026 @11:02PM
(#50555938)
An impressive showcase of productivity theatre in which tokens are incinerated in exchange for software that is always never "finished" and will continuously let down its users.
Some people have cleverly parlayed this new fad into money, but this is typically a result of their sales techniques rather than their software.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by xtracto on Wednesday November 18, 2026 @11:56PM
(#50556218)
Just tried this today. Installed gascity, set it up with "gastown" settings, added a couple of repos and pointed it to a [bot to crazy] jira ticket .
It just make things so complicated... and in the end I had to chat with the "major" interactively, and I didn't see any benefit vs a simple claude session + a "work with 10 agents" prompt. It just seemed complicated for the sake of it.
I want a system that hides the complexity, and is effectiveand efficient. But we're still not there.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by pkulak on Thursday November 19, 2026 @12:07AM
(#50556276)
I never use long running sessions. I like one small task at a time that I can understand and evaluate. If the only downside is worse one-shot GTA homages, that’s a pretty good trade off.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by jdw64 on Wednesday November 18, 2026 @09:14PM
(#50555223)
I’m considering AntiGravity because its subscription usage seems lower than expected. But personally, with Gemini’s Carbon, Hydrogen, and Neon, it’s confusing because they don’t show which model is mid-to-low-end and which is flagship. OpenAI’s model names—Astra, Sol, Terra, Luna are intuitive, like cosmos–sun–earth–moon. Google’s model names aren’t intuitive. If we go by abundance, Hydrogen should be the top model.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by ijidak on Thursday November 19, 2026 @12:03AM
(#50556258)
It's wild that Google can fumble something as basic as heirarchical naming.
I have no idea whether argon, carbon, or neon is their largest/best model.
If they think we're going to pull out a periodic table to understand the naming scheme, they shouldn't be in charge of product.
All of the providers have chosen a somewhat nerdy naming scheme, but that's fine given the current mostly tech customer base, but at least Anthropic's and OpenAI's are intuitive.
But, the order of elements in the periodic table is not something most people have memorized unless you do something like hydrogen, helium, lithium, maybe.
Or maybe iron, copper, silver, gold.
Maybe at least pick elements that are in horizontal order, like carbon, nitrogen, oxygen.
Just so many basic mistakes in every aspect of product rollout at Google.
Re:Gemini 4 Neon looks like an Opus 5.5 competitor
by jdw64 on Thursday November 19, 2026 @12:21AM
(#50556361)
I hit the upvote button.. These days Google seems focused on B2B and not interested in B2C. Honestly, it’s too non-intuitive. Before even memorizing the periodic table, it feels a bit ambiguous. It’s not even that they get bigger in order of atomic number.
For this model, I mean. And not the Anthropic IPO.
All the rest I have seen are victims of benchmaxxing and therefore simply misleading.
Genuinely hoping some people sign up from this and use the app so we can get some more high quality data (it's open source: https://github.com/bottomless/agent-duel).
But that's about as complicated as I get. I have recently tried to use Copilot because that is what work wants us to use, and even with Opus 5.5 it is noticeably inferior to CC on the same model. Wild. So clearly the harness matters.
For what it’s worth, the linked article data (Agent Duel data) is all run on OpenCode. I’m curious if people would prefer we run each model in its native harness (at the expense of user experience because it’ll be buggy).
Here is an example from FrontierCS bench: https://x.com/wenhaocha1/status/2114559544156205413
My company is slow-walking (and that is an understatement) our LLM usage, so the majority of work that I'm reviewing is human generated. After the stories I hear of what other people are experiencing when management is more enthusiastic, maybe I should count myself lucky.
- SWE-bench Pro (hard 51): 39.2% → 64.7%
- Terminal-Bench 2.1: 39.5% → 55.8%
https://huggingface.co/harness-hub/Qwen3.8-27B-pi-adapted
If this were true, models would do way better in their own harness than in others, which doesn't seem to be the case (effect is minor).
Your link has a "link to the release blogpost" which is supposed to explain the training recipe but the link is down.
The big “aha” moment for me was seeing the wildly different results I’d get using something like Claude Design vs just prompting (even when using leaked system prompts). I then started hearing about the special harnesses available for biotech, science, and math that seem to be available for researches via OpenAI and Anthropic directly… which sort of further cemented in my brain how important it must be. I wish I got the same quality from Cursor, or OpenCode, as I do Claude but I just don’t.
"OK, google models perform just as well, are faster and are cheaper but all that doesn't matter. Because the models, now that Google has very good ones, doesn't matter after all. All that matters is the harness".
And of course it's upvoted by the Anthropic shills.
I must not be deep enough into the conversation to get it. I was just sharing my own perspective. I don't follow AI development nearly as close as a lot of HN does. I don't hate it, but I don't love it either, it's just part of my job now.
> And of course it's upvoted by the Anthropic shills.
Gotta tell you, my post is barely above water ;-). It goes up, goes right back down, plenty of people seem to agree with you that I'm being mean to Google or something.
Have they edited their comment since you replied? If not, this is one of the most egregious strawmen I've seen this week. You have brought a lot of your own baggage to this discussion, and stuffed it into a comment that said approximately none of what you claim to have taken from it.
You get the same with antigravity and you get your whole Google account banned
To be fair, I don't have the model either but after reading this I will give it a try since Opus 5.5 is my go-to right now.
(Also, out of curiosity, how are you funding this free inference for frontier models Is this not massively abuseable?)
In the battle, if side A finishes before side B we allow the user to vote for A before B finishes. (This is contrary to Arena.ai methodology, but I think it's the right thing for agents when sides can take a dramatically different amount of time.) This is why DeepSeek 4.1 Flash is doing so well in our leaderboard, it's super fast and often sufficient.
> and a "developer vote"
This is confusing, sorry. Inspecting our data it's almost entirely people doing software developments with agents. It's just a vote.
> (Also, out of curiosity, how are you funding this free inference for frontier models Is this not massively abuseable?)
This is a pivot from Bottomless (YC W19). That business is doing okay and funding our runway, in addition to fundraising back in 2021.
Second, I will be trying this with agy when my Opus 5.5 limit hits. I only hope its faster than Argon which is already dog slow
"It looks like he's dead."
"...He's covered in blue paint, or something."
We’re reaching the point where certain models are really good at 1 thing. The person writing this blog post isn’t using Neon for large-scale orchestration, but I’m sure it excels in its usage. For me Fable 5.2 as the orchestrator and Opus 5.5 and grunt workers have led to the most robust software...so far.
I'm the person writing this. This is head to head battle data by real developers on top of OpenCode. The data is generated by an open source app so you can inspect it yourself (https://github.com/bottomless/agent-duel). The hitch is there's no real Neon data. This is purely projecting from Carbon's super slow but very good performance onto Neon's likely fast and likely equal performance.
Some people have cleverly parlayed this new fad into money, but this is typically a result of their sales techniques rather than their software.
It just make things so complicated... and in the end I had to chat with the "major" interactively, and I didn't see any benefit vs a simple claude session + a "work with 10 agents" prompt. It just seemed complicated for the sake of it.
I want a system that hides the complexity, and is effectiveand efficient. But we're still not there.
I have no idea whether argon, carbon, or neon is their largest/best model.
If they think we're going to pull out a periodic table to understand the naming scheme, they shouldn't be in charge of product.
All of the providers have chosen a somewhat nerdy naming scheme, but that's fine given the current mostly tech customer base, but at least Anthropic's and OpenAI's are intuitive.
But, the order of elements in the periodic table is not something most people have memorized unless you do something like hydrogen, helium, lithium, maybe.
Or maybe iron, copper, silver, gold.
Maybe at least pick elements that are in horizontal order, like carbon, nitrogen, oxygen.
Just so many basic mistakes in every aspect of product rollout at Google.