I'll use this opportunity while it's still early to share my experience with Argon.
I got it via the "Pro" plan, exclusively for personal task usage. So no agentic programming.
For starters, the limits are dreadfully low. Five messages on medium is already enough to trigger a 4 hour cooldown. Secondly, the best part is the integration with Google search and Maps. Makes it seamless for trip planning. Lastly it's the only "SOTA" model in a long time that has actively hallucinated details. I don't know if it's because the Gemini harness is not asking it to verify information, but I've had some real Deepseek V3-like lies in responses.
Either way, I find it difficult to get invested in Gemini because nobody will have access to Carbon for a few months anyways.
I similarly had Argon respond with a vast hallucination. It surprised me because it wasn't a little wrong on the details but a fully false verbose response that completely fabricated fabricated everything. I'd recently had Claude Code help me create transcripts for some audio notes from my mother in law and decided to see how some other models would handle the same task sans harness. Argon made up a long conversation from a police sting operation with under cover operatives seemingly just because it read the file names and identified that they would have come from a recording device.
Honestly the fiction writing was pretty impressive!
Suddenly very curious what the llm roleplay people think about this one lol. Fortunately I've already learned to stifle my curiosity on this specific subject.
But my experience is that the agent matters a bit more than the model. It is fun on ChatGPT because of its recent (?) bias to always be creating images for conversations around fiction.
It goes way back, I work in AI/Ml (taken over by transformers/LLMs) space since early days of this "AI Summer". We get some nice grad school students interning from top universities. I met one during a trip to the office, from top notch school, introduced me to Triton programming when it first came out. It was early days of LLaMA just coming, when The Bloke was regularly dropping finetunes, I was joking asking him what the hacker stack was for "AI waifus" that the cool kids were using. Lo and behold he drops the name of the SillyTavern project. Which later was really educational in setting up local inference servers and in other ways, may have had to, ahem, delete some browser history.
If you uploaded the audio via the web site or app and got terrible results I'd bet Argon wasn't the model doing the transcribing. The only way to know for sure is to try again with the API.
> because nobody will have access to Carbon for a few months anyways
From Google saying that Argon would be 'available soon' (as they did just now for Carbon), it took them 13 days to release it. So... unclear that Carbon won't see the same trajectory.
Yeah... Given that everyone else seems to make models available either immediately or within days of announcement, idk why Google feels it's competitive or acceptable to do these 'available at some point' releases.
Capabilities are also improving so fast that this fomo doesn't really keep people excited. If I can't run it, I'll sorta just click off. And given how they handled the Argon release, I've not even bothered look at this Carbon one. Fully expected it to not be usable yet.
The other labs do the same process, but they don't announce the model until it is about to be released. For some reason Google is announcing at the start of th process.
My guess is Google knows it is (way) behind the and needs to keep drumming up interest. Although at some point it becomes counterproductive (raising "yet another not available model; is it vaporware" vibes).
Creating a false sense of scarcity is essential to get people talking about it. I get almost endless inquiries from peers now that I have access to Mythos.
Eh, maybe I'm too much of an AI safety person, but I'd rather the labs be forced to announce when they are working on large SOTA models like they are a clinical trial. That way if it's never announced they have to say something like "training didn't work out" or "it took over the server farm and we had to burn the hard disks".
hmm, I haven't tried Carbon yet. But I have been using Argon on and off via agent-shell - https://github.com/xenodium/agent-shell and unofficial ACP client.
I am also using it via Google pro tier and did not immediately run into quota issues. But as someone else said in previous discussion of this - Google Pro tier already includes lot of stuff (including Youtube premium etc), the AI plans are just a nice addon.
That's the problem for me. Google can have the world's best model; it doesn't matter to me, because I effectively can't use it.
Both Opus 5.5 and Sol 6.1 are extremely good and provide a lot of inference on their $200 plans, and then there are the Chinese models - DeepSeek 4.1 Flash, MiMo, and StepFun all offer a lot of value per cost.
At the moment, I don't see a niche where it makes sense to use Google's models, regardless of how good they are.
In my experience, (using 3.8 flash) the Google models do a fairly good job at summary notes and simple documentation (do this, do that). It doesn't seem to be as bad as Claude for producing headache-inducing text.
> I find it difficult to get invested in Gemini because nobody will have access to Carbon for a few months anyways.
I feel like you're being overly dramatic here. Argon was 13 - 15 days.
Argon was announced September 30, made available on October 13 to Ultra everywhere, and Pro in the Gemini App. Pro plans got Argon on October 15 in AGY.
This is the first time they've slow-rolled a model. Who knows how long they'll wait on Carbon.
The Ultra-lite plans ($99/month) get some pretty good quota where you can actually use Argon some more. Maybe Google shouldn't be grouping together plans, but it should also be noted that $20/month also gets you 5TB of storage on Drive. If you paid for Dropbox, you get 3TB for $18/month (without any AI model usage).
If we go back only 45 days, Opus 5.5 was not even out yet. So for more than a third of the current SOTA model's existence, Google's response to it was under its own embargo. When it was finally out, paying users get 3-4 prompts a day, which means Argon will be experienced by a tiny minority of people, another unforced error on Google's side.
By the time Carbon comes out, I fully expect Anthropic, ChatGPT and/or a Chinese lab to have its answer ready to ship in less time than it took Google to approve a release.
Since you're a googler, can you trigger some internal process to improve the connection between google services?
Gemini cannot create "my maps". I like creating a map of stuff for travel and now I ask it to create an importable file (which it doesn't always get right) but it should honestly do that itself.
And I don't mean that from within the Gemini app, I'd like a shareable list of places, which you can do via a very outdated maps UI
I have 160G of screen captures from Tumblr from my then angsty teenage kid. I think my spouse takes a few Gig of photos for each outing we go on. Several people dress for fancy thing via a process involving many clothes changes and even more selfies.
In my experience with antigravity-cli for coding Argon gets the task finished much faster than 3.8 Flash and with a higher quality output. The quotas on Pro are about 2 hours of usage per week for Argon. Its a really nice model to use. Only thing that is annoying is that it still struggles with tool use on the gemini website.
Same. I subscribed to Gemini pro and requested a refund literally the same day. Asked it to put a technical image on a presentation (gave it the image) and it kept generating a different image of a peaceful landscape... Yeah, very pleasant but totally unrelated.
It's kind of an odd release. Yes, it's technically the top intelligence model by like one point above Claude according to Artificial Analysis, but it's like barely cheaper?
It looks like the best sort of bang for your buck is still GPT Sol and GPT Astra. Claude and Gemini have just been going for that number one intelligence spot by sacrificing a lot of efficiency.
It does sort of show their hands a bit that their larger goals might be outside of just consumer sales but also seeking hyper intelligence that could bring value in new ways of discovery (if it ends up being a legit outlet for such things consistently)
Yeah that "Pro" usage is a joke! I wish google paid more attention to what the people want! it's a shame I loved Gemini 2.5 and 3 when they first came out they were super amazing!
Agreed on the limits, they're quite frustrating. I've still been preferring Argon to Opus 5.5 though, because even though Argon gets details wrong, I find that it's much more creative and willing to explore ideas. In my experience Opus tends to be rather condescending and won't make room for less orthodox ideas to develop. For what I'm doing, I'd much rather have good ideas that I implement mostly by hand rather than regressing to the mean and have the LLM write the code.
>Lastly it's the only "SOTA" model in a long time that has actively hallucinated details. I don't know if it's because the Gemini harness is not asking it to verify information, but I've had some real Deepseek V3-like lies in responses.
I don't know what it is about Google models, but they are the worst at hallucinations. I don't understand how they can so consistently be this bad.
Gemini models always suffered from this. They were almost always best in terms of intelligence, but one of the worst to use in practice, because they have a lot of failure modes on simple tasks that simply give factually incorrect answers, or completely break and output gibberish.
> Lastly it's the only "SOTA" model in a long time that has actively hallucinated details.
Yesterday I used Google AI-Search (so Gemini Flash 3.5?) for opinions on a traffic accident and it continously constructed law-interpretations and then referenced the wrong paragraphs. It talked about rules on road-crossings and cited paragraphs pertaining to alcohol intoxication as sources.
Note that Argon was rolled out for IDEs for people on paid AI Pro on Oct 15/Oct 16 (a couple days after Ultra users), but of course, usage limits are extremely low
I have experienced all of this too. I also find Argon still seems to have the sycophancy problem that some of the other labs have stamped out to a large degree.
It is expensive as hell. That said, on my weird personal benchmark (https://botbowlbench.com/) it reliably beats Opus 5.5, which surprised me a fair bit.
It's terrible. I tried it via API in OpenCode. It's so slow, and the lack of reasoning output makes it feel even slower. And I also noticed the lies. I gave it a high-res image of a map to classify labelled locations, and it started going on about how smart it was for the map creator to use squares as the symbol for one of the categories of labelled places, and gave me a list of all the places with squares along with their category, but the map has no squares. It's circles, triangles, and stars.
I am having a very positive experience with Argon: since it was launched I accessed it through Ultragravity and connected via a Google Cloud account. For one month I have been trying to move the needle in SHA256 cryptoanalysis with Claude to not avail and Argon moved "two needles".
Since then I tried it for experimenting on diverse fields. For example, this week there was a discussion here in HN about the non-continuation of Python funding on the JIT, so I "played" again to removing the GIL and moving to the JIT in Python, it did it. I played with many other things, even the Riemann Hypothesis (it just removed their rational parameter rounding only moves 0.875 towards 0.87495702, nothing significant though).
Many other relatively great things were done this week in parallel. I have some budget for research.
Trip planning is the most often used use-case for agents/bots I see in marketing. I'm lucky to travel once a year, but if I did have a trip, I wouldn't feel comfortable letting an LLM take the wheel. Too many variables for wrong flight or room, closed locations in itinerary, etc.
Now, critical server infrastructure? Sure, have at it Claude, make no mistakes!
I would literally never let an AI plan my trip. I do have very specific interests though and it's nice to have an overview of suggestions of places to go.
Plus, it's great at researching the history of places you're visiting, so you can find cultural experiences a bit easier.
I don't travel often, but I do live in Europe where it's easy to visit a new city or country in the weekend. This makes this functionality a quite common use for me.
I mean this specifically for general tasks, like personal research. Small stuff. I was asking for espresso machine recommendations and it literally came up with a non-existent machine that supposedly met all my requirements. I've never seen that with ChatGPT, Claude or Kimi. It's quite surprising how it did that _after_ doing a Google search.
It has already become irrelevant to anyone paying attention. Raw scores at published benchmarks mean next to nothing in modern use. They are either gamed to hell or unsolved to the point where differences can be explained by randomness. Speed, cost per token, tokens per task and hallucination levels are the useful axes you can compare along these days if you're not doing scientific frontier level research.
They probably prefer being used by the deep-pocketed organizations that have access to Gemini 4 Carbon even if it means losing the entire rest of the market.
Also, their tooling still is complete shit. I'll not be forced to use Antigravity thing even if it is available and clearly better than Opus or Astra. Their subscription is useless. API can be used with anything you got but that's gonna cost.
You should be running your own benchmarks often given the nature of these products. Releasing these models whenever with whatever corresponding benchmarks provides you no assurance that things will stay the same.
Having a great time with an ice cream brand at a store is no assurance against hollowing out the brand tomorrow.
This is the only use case I've found it superior to ChatGPT or Claude for - helping me understand higher level math. It's slightly easier to understand than the other models
Not OP, but I asked Gemini 3.8 Flash this question (via self-hosted LibreChat) and got an excellent answer:
I'm trying to figure out how heat dissipation works. Specifically, I have a block of aluminum with extruded fins (as a heat sink) and I'm trying to understand how many 30-watt LEDs I can place on it. I have a fan as well, and I'd like to understand how fast I need to run it at different power levels (the LEDs are dimmable). I can gather measurements empirically (which I'll do), but I also want to understand the basic mathematical basis I should use for estimating these values.
Just talk to 3.8 flash about whatever (caveats: ancient knowledge cutoff of jan 2025, small parameter model so if niche '90s korean animated series is your jam, it's gonna be rough). The model is a real joy to talk to, I even will feed it SOTA model output to clean up and clarify for me.
Its the first model ever that I have been worried about a successor losing the "feel" that it has.
Carbon scoring below Opus 5.5 on coding highlights how magnificent Opus 5.5 is as a coding agent. With just a $20/month sub, it performs a ton of work at a very high quality.
The benchmarks of a model that hasn't been released yet are definitely suspicious.
I also think Google should stop "releasing" models that aren't actually available. For their own sake, because by the time Gemini 4 Carbon becomes available, nobody will notice. There won't be a new press release or much excitement around it.
There's an issue with this index where many models are listed in the model chooser, but missing from the index. E.g. Qwen 3.8 Flash Next is listed but missing, as are older Claude (4.6, 4.5, etc) or OpenAI models. This makes it a bit tricky to see the improvements over time.
They removed Qwen Flash Next and GLM Flash from their benchmarks, as of two days ago. They're not publishing any figures at all for them (they show as "N/A").
edit to add: It's very disturbing, because these open models (GLM particularly) were among the best of all LLM's on their benchmarks. On the intelligence/cost frontier, specifically. Archive.org remembers that GLM Flash was in their green quadrant just a few days ago, next to Haiku:
well if there was any doubt about why openweight models were ranking lower on every iteration of the benchmarks... this should remove all doubt. to just flat out remove is very overt
I want to talk about my experience with Argon, noting that I used it via OpenRouter on a Raspberry Pi, spending around $15 in credit.
My experience is that Google is aiming to create a generalist model – but a truly generalist one!
In fact, I find it particularly accurate in general terms and even in long conversations, maintaining excellent consistency and a wealth of information in response to complex questions.
I’ve tested it both as a coding agent – though, precisely because of what I mentioned above about its ‘generalism’, I don’t think it measures up to Fable 5.1 or Astra – and I’ve really appreciated its qualities when supervising my agents’ activities. It was able to keep track of them, suggest alternatives, and monitor the entire lengthy process in parallel without ever straying too far from the request or losing the thread – as often happens with Claude and OpenAI (you only need to test it in Claude Code itself, in both Ultracode and the agent team mode – albeit experimental – to realise how, once the task gets underway, both of them lose their way).
It kind of doesn’t make sense. Modern google is typically kind of bad at building products and very good at getting them in customer hands. This is the opposite of that.
It does make sense, when you consider that Google had its earnings report yesterday, and missed its targets. $GOOG is already down 13%. It's an announcement purely for their investors.
I remember when Opus 5.5 came out, we had a discussion about whether it was nerfed a week later [1]. It's not possible to do so with Gemini 4 models since none has been made available the day it is announced.
Without us being able to access Carbon when it is announced, there's no way to know the Carbon we get a few weeks later is the same thing as what has been benchmarked here. I think benchmarks should verify what is benchmarked is exactly the same as what's been released.
Gemini 2.5 flash and 3 flash were highly underrated models that performed way better than the peers and we used the hell out of them.
Since then none of the Google models have competed well with the others at their price points. Long context performance drop, instruction following issues, unnecessarily complex and sloppish outputs.
Argon is no different, it feels just an iteration better than 3.8 flash. I don't trust the AA ranking yet.
I agree. Flash 3.8 is not good and actually quite expensive, given its tendency to overthink everything. We've been transitioning lots of workloads that were formerly on Flash to Haiku 5.5. Great model.
Even with gemini 2.5 or so i remember the models used to just simply hang in production and randomly used to collate tokes and give in the output stream vs giving one by one which was weird.
Also the guardrails were implemented in a very bad manner. By default the models used to raise a default guardrail error on basic queries.
You know what. When Gemini 3.1 Pro Preview came out it was better than Opus at the time. It was my main model for 3 weeks.
Until it got lobotomised. Then it lost most of it's capability.
Similar situation happened to Anthropic's Fable. It was an amazing model until Opus 5.5 came out.
So now, I'm not even looking at a "new" model until it is a month or two old. By then we will know if they will destroy ability to make it cheaper to host.
Since 3 Pro we already know that Google's model are very good in benchmarks, but when you start programming with them... not really good and each model has its quirks that make me continue the project with something else, once I fixed gemini's bugs.
The time between public announcement -> public release seems to be a tacit admission that Google is still a bit behind the frontier labs. Google is justifying the delay by pointing to cyber risk and a closed-access period reserved for analysis of safeguards. I'm dubious of this justification. But if it is true, I'm pretty sure the other labs are doing similar sorts of things in private. I think most of us prefer it that way—if Anthropic public announced Fable 5.5 two weeks ago with no availability that would add to my annoyance. Maybe they learned their lesson with Mythos, or maybe it's just that Google also does not have an IPO looming. Who knows?
I tried Argon for a large historical HTR transcription project recently, since I heard it was really good at this. It was really good, but like all top US models I've used it was
* Definitively very good at domain specific knowledge. It can read sloppy 19th century danish gothic handwriting with faded ink just fine. Not perfectly, but probably better than I could have done with a day of struggle for every page.
* Expensive.
* Bad at actually doing what I said. I had told it in the prompt to be careful not to miss text, but I hadn't explicitly told it that some images may have text in double-column layout. So on those images - over half of my 300-page document - it produced an excellent transcription of the first column, and then considered itself done. Want to try again with a more careful prompt? That'll be another $20.
For ocr, you have to practice, practice, practice with your prompts on small sample sizes before one-shotting a book. I create a json schema for the output that describes the structure in detail (using ai from my prose descriptions of structure of course). I have specific tough pages I use on openrouter to test every new model I am interested in. Gemini has and does absolutely dominate for this. But flash can be better because it doesn't overthink things.
I did do test images, but apparently not enough. It's not 100% of images it drops the second column on either. On many it gets both, on some it only gets the second column.
I also found that it ignores other instructions sporadically ("Don't use letter variants or ligatures in the output, use the normal Danish/Norwegian alphabet when at all possible", still a few Unicode tall s'es in the output.)
It's good, but it's so frustrating since "worse" models manage to follow such instructions much better.
> They are like almost like malicious compliance geniuses lol.
They're like a monkey's paw or evil genie I think.
You'll get exactly what you ask for, but lots of weirdness you didn't expect.
To be fair to the model makers, deciding what to do with an under-specified prompt is hard, particularly in an RL environment where you can't just ask the user.
For stuff I want to run for a while, I'm defaulting to telling it to ask me the questions upfront to reduce the incidence of these kinds of problems.
Just so everyone is aware of the "coincidences" that happen with this index:
- Two days ago AA announced their v5 Index which added a few new benchmarks and tweaked a few things.
- Today the newest model announced from a big lab tops the charts.
I'm not saying that AA is definitely taking money from the big labs and changing the benchmark to make the labs' new models look better, but it kind of looks that way. This pattern of behavior has happened before, where the index gets tweaked right around when a new model comes out, and the new model is on top. AA does not, AFAIK, provide a way to see how the new models would have scored under the older index versions. You could probably calculate it yourself, but I'm not going to do that much legwork just for an HN comment.
It's interesting because they publish the index methodology, so you can't really accuse them of not being transparent, but I don't really believe that the choices to update the index were completely independent of the model they happened to be evaluating at the time.
Related: The DXOMark camera scoring method also had similar behavior, where they would release new testing methodology right before flagship smartphones were released. Again, they are technically being transparent about the process, but it kind of smells like the "independent" testers may not be as independent as the average user would hope.
I had a look at the changes and the biggest impact seems to be from adding Terminal-Bench-science 0.1 and having it contribute 15% to the overall score.
I have no doubt that these are very relevant task for people in those respective fields, but I suspect they have next to no relevance to some 99.9% of model users. Hence why especially smaller labs with smaller models didn't really train for such use cases and you can see it.
Personally, it's not something that matters at all to me, as I don't work in cheminformatics or bioinformatics.
This is also arguably more of a test of a model's knowledge base than reasoning ability.
But most importantly, there is also the question to which extent the aggregate score then remains a meaningful result when you mix up too many too disparate benchmarks.
The coding agents subindex, in contrast, looks at least superficially plausible [1].
True, but coding is where something like 80%-90% of their revenue comes from; few other use cases are as token-hungry, and none of those are nearly as widespread. Many users will of course use the models just as chatbots, but they don't generate much in terms of revenue. And that is ultimately what determines where labs focus their resources.
Yeah, it is very suspicious. Each time they update their ranking algorithm, the closed models from US labs jump up and any previously high ranking open model jumps down. It happened with MiMo, Kimi, GLM. All were right there amongst the very top, and each time that happened, AA followed quickly with an index update that shunted them dramatically lower.
Check out vals.ai for an alternative. Not sure how independent they really are either, but it's at least good for a cross reference.
We’re literally talking about the same thing, but ascribing different motivations.
I do think the test a new model and realize their index is broken- the new model isn’t on top, so they change the weights to make sure it’s on top.
The difference is that you seem to think they are doing so out of some innocent feeling that the new model is actually better, while I think they are doing so because they were paid to do so. I think my interpretation is more likely, but that’s just me.
And how do they realize their current index is broken? They either have some recency bias, or indeed favor the big American labs (more likely, since a new Chinese model topping the charts triggers a shakeup).
It's odd because I wonder if anybody actually cares about such scores. It's not like millions of end users look at the score and use it to make a decision what to buy. Subscriptions can easiliy be canceled and people anyway use the models they "feel" work best for them. Hardly anybody I know uses an even remotely scientific method to evaluate model performance. It's mostly vibes with a little bit of (mostly flawed) A/B testing sprinkled in.
I think part of it is to justify capex. "Yeah, we spent x billions on this, but look, we have the best models, we're beating OpenAI and Anthropic, we're winning, it's all worth it!"
My paranoid impression was more that the updating and addition of tests — obviously essential in this game — was delayed to provide advertisement for Kimi K3.1. The same happened for K3 — and this is why it was famous — but its position had collapsed by the time of 3.1
This is just a hunch since I have not used Argon very much, and I have not used it for coding (deepseek 4.1 flash 1017 with dsh, and qwen 3.8 max are so good for coding tasks that local models have difficulty with).
My hunch is that Google will end up being best for non coding tasks. Google can concede coding to other vendors who pay Google for infra.
At this point frontier models are good enough to be a pair programmer. But only OAI and Anthropic offer good limits. Maybe they're burning money but if the Google limits are the future of usage style accounts then we all have to get used to API
They have top of the line research, I mean, they invented the thing, and they are still doing stuff that goes beyond making a bigger LLM, as it seems to be the only thing the others are doing, research-wise.
They also have hardware capabilities no one else has, they invented the TPUs, and have lots of them.
They also have the brand recognition, ecosystem, user base and lots of money.
So why are they lagging behind on the actual products, and by lagging behind? I mean they are always in the position where they are just behind the frontier, but still in the game.
It seems almost deliberate. Maybe they are playing the long game, waiting for the bubble to burst. Maybe they don't want to compete against the more profitable parts of the company. Or maybe their researchers are not interested in making an actual product unless being forced to.
People always love to think the AI race is a duopoly (OpenAI vs. Anthropic), but from what I have experienced, Gemini was always holding on its own, and I find myself using it more than Claude.
True, I use LLMs as glorified search engines to unearth material to read myself, but Gemini is much more useful if you decide to learn yourself. It also offers interesting expansions to your questions.
While I don't offload my work to LLMs (e.g.: Write this project, I'll be watching TV), I find them useful for closing my knowledge gap by collating information, and Google's Gemini is good at that.
I have Gemini because of my Google One membership. I already was on their 2TB plan and it gave me Pro level, IIRC, and it was generous. Now I'm on Ultra mostly because of Google Drive storage I get, but Gemini also gets a nice boost, as well.
I'm on $20 Claude plan, and it's also ample for my needs, for now.
I think this is because of capacity issues. Higher paying per token users probably get preferential capacity allocations to those on monthly plans. The allowance for what you get in the monthly plan increases as the models age and the likely capacity problems improve.
The $20 plan gives you ~120 minutes of high thinking time from Argon weekly. Thinking time isn't an exact metric, context size matters a lot, but I have been using it on the $20 and still have 25% left with ~85 minutes of thinking time on high for a project I have been working on.
They have an insane amount of resources but are so bloated, have a ton of bureaucracy, and have lost a lot of their top talent. Looks like they have figured things out now though.
Not everything is writing code and search. My uncle works in mortgages and the (very large) firm he works for is entirely Gemini. The way he talks about it is with wonderment in his eyes while he goes into detail on how it went through multiple documents and found unaccounted for cases. I think Google is doing fine in these kinds of industries.
I wouldn't even bet that Google is better than OpenAI and Anthropic for these categories, but they seem to be well used outside of our direct space.
Artificial Analysis is not trustworthy anymore. Every time an open-weight model, especially Chinese, looks to be nearing the top, AA updates the index to (ostensibly) specifically push closed models higher. Just recently with v5, OpenAI models were pushed up.
> I think what's happening is Chines models genuinely try to benchmax on it and hence they suffer when a new version comes out.
I read somewhere on Substack that a lot of this was driven by the inclusion of more knowledge work benchmarks, where the US labs are stronger, versus coding which is where most Chinese models appear to put their energies for now.
Or it could be that the benchmaxxed models are getting pushed down by the introduction of unsaturated benchmarks. Muse Wonder also went down 52 -> 43 after the update.
It's not that hard to create your own uncontaminated eval for the problems you care about, and compare.
Here's mine for coding in Rust, and I definitely see the same pattern of "most chinese models do much worse than on public evals that have been around long enough to train on" that AA v5 surfaces: https://slopcop.com/power-ranking
I haven’t tried Gemini for coding yet. I did consider buying their subscription, but based on what I’ve seen from other forums, Gemini has never been a frontier in coding, even with good “benchmaxing”.
why do i not see as much traction and stirring up on the internet for gemini models as much as claude or gpt even though on bench's they are very much THE frontier. is the reason very limited access early or or just not enough publicity or hype as the other labs do?
I mean, that's the main reason. How would you expect to see the kind of hype that Claude or GPT can generate when nobody can use it? The hype of those models are primarily generated from people using them to build impressive things and share those results. Can't do that with an unreleased model, right?
Beyond that, it seems a lot of people have learned that these agent leaderboards really don't tell the whole story. They're a good litmus test, per se, and there's plenty of hype being generated around these scores as-is. But anybody using AI in practice knows that benchmarks can only say so much, and one model scoring better than another doesn't necessarily imply that that model is actually better in the ways those people care about. You can see that in this thread as people are pointing out that even these benchmarks seem to suggest that Opus 5.5 is still leading in coding (which is what a lot of people, especially on HN, ultimately care about).
>just not enough publicity or hype as the other labs do?
Well, it's effectively both. Google is certainly not that pressed to generate as much hype as these other companies. They can afford to take their time. It's also worth noting that Google is definitely targeting different consumers, investors, etc., so their strategy will definitely be different.
For what it's worth, I've been using Argon since it's been available in Cursor and I really like it (at least at its current price). I think Google really did close the gap a meaningful amount (maybe not all the way, but enough to prove they're still in the game). Carbon being significantly better while being the same cost is pretty exciting to me. But until I can use it, I don't really care about it.
Google has to get it's shit together. All the stats and charts doesn't mean squat because when I try it now on a provider all I get is trash :(. Makes me question these metrics entirely and really makes me question the authority that google used to perceivably have.
I don’t care and in my opinion AA does a disservice to their users by allowing such blatant manipulation. What would happen if every AI company were to include their unreleased models like this? Put the unreleased models on a separate page and leave the headline benchmark rankings for models that you can actually use.
It's unobtanium so nobody should care about it. Any frontier AI company can nowadays create models with ridiculous resource and token usage that will get extremely high scores, but they're of no use when you can't use them.
I take this opportunity to give feedback on Argon. The limitations are a problem. I have a Pro subscription and Argon already stops working after 3-4 prompts with long delays afterwards. It's virtually useless right now even when you pay monthly for it. It is better for some tasks than 3.1 Pro, though. Not much in my experience but it can sometimes fix errors that 3.1 has problems with. I never use Flash models since they often give abysmal results.
I use it purely for finding stuff in text documents and OCR, at which it excels, but I've found that for any kind of analysis it's some bewildering mixture of smug, defensive, paranoid, cheerful, and wrong about everything.
I feel like the headline here is "the Artificial Analysis index is becoming an increasingly poor measure of capability, having previously been quite good".
"We're taking a deliberate approach to rollout and are actively engaged in the U.S. government’s voluntary process for pre-release model testing. Starting this week, we will make Carbon available to a subset of cyber defenders and will gradually phase access to additional trusted partners through our Fairwind Program. We’re continuing to gather feedback and iterate on guardrails before making Carbon available to developers, businesses, and consumers via our product surfaces as soon as possible."
These benchmarks and rankings seem more noise than signal these days. They're uniformly divorced from sincerely-attested real world experience. And the real world experience isn't driving any consensus either.
So here's a meta-benchmark: at what point does the act of choosing an LLM product for a reasoning task become less reliable (in the sense of "predictive of future success") than hiring a human being for that same task? Have we already cross that threshold? I think we might have.
And once we do... what happens then? Will the truly elite models be hidden in a sea of mediocrities simply because the goofball "managers" doing the hiring are too dumb to recognize their genius?
By the time this model is available for public use I'd imagine it won't be #1 anymore, which is pretty sad. Even when Google gets back on the ball they seem to find a way to fuck it up.
A secret model I trained last afternoon is the actual #1 on benchmarks.
No, you can't use it. You can't even see it, and I won't provide you any information. But you must trust me that I am the genius who made the best model in the whole world.
Spare me the celebration. Artificial Analysis should not be granting any company the favor of a #1 ranking for a model that isn't released to the public.
Google's model release is pure PR puffery. It's no coincidence that it was released on the day of its earnings call.
I'll use this opportunity while it's still early to share my experience with Argon.
I got it via the "Pro" plan, exclusively for personal task usage. So no agentic programming.
For starters, the limits are dreadfully low. Five messages on medium is already enough to trigger a 4 hour cooldown. Secondly, the best part is the integration with Google search and Maps. Makes it seamless for trip planning. Lastly it's the only "SOTA" model in a long time that has actively hallucinated details. I don't know if it's because the Gemini harness is not asking it to verify information, but I've had some real Deepseek V3-like lies in responses.
Either way, I find it difficult to get invested in Gemini because nobody will have access to Carbon for a few months anyways.
I similarly had Argon respond with a vast hallucination. It surprised me because it wasn't a little wrong on the details but a fully false verbose response that completely fabricated fabricated everything. I'd recently had Claude Code help me create transcripts for some audio notes from my mother in law and decided to see how some other models would handle the same task sans harness. Argon made up a long conversation from a police sting operation with under cover operatives seemingly just because it read the file names and identified that they would have come from a recording device.
Honestly the fiction writing was pretty impressive!
Suddenly very curious what the llm roleplay people think about this one lol. Fortunately I've already learned to stifle my curiosity on this specific subject.
I will try here: https://myownlore.com :)
But my experience is that the agent matters a bit more than the model. It is fun on ChatGPT because of its recent (?) bias to always be creating images for conversations around fiction.
It seems a strangely underdiscussed topic on HN.
It goes way back, I work in AI/Ml (taken over by transformers/LLMs) space since early days of this "AI Summer". We get some nice grad school students interning from top universities. I met one during a trip to the office, from top notch school, introduced me to Triton programming when it first came out. It was early days of LLaMA just coming, when The Bloke was regularly dropping finetunes, I was joking asking him what the hacker stack was for "AI waifus" that the cool kids were using. Lo and behold he drops the name of the SillyTavern project. Which later was really educational in setting up local inference servers and in other ways, may have had to, ahem, delete some browser history.
If you uploaded the audio via the web site or app and got terrible results I'd bet Argon wasn't the model doing the transcribing. The only way to know for sure is to try again with the API.
> because nobody will have access to Carbon for a few months anyways
From Google saying that Argon would be 'available soon' (as they did just now for Carbon), it took them 13 days to release it. So... unclear that Carbon won't see the same trajectory.
Yeah... Given that everyone else seems to make models available either immediately or within days of announcement, idk why Google feels it's competitive or acceptable to do these 'available at some point' releases.
Capabilities are also improving so fast that this fomo doesn't really keep people excited. If I can't run it, I'll sorta just click off. And given how they handled the Argon release, I've not even bothered look at this Carbon one. Fully expected it to not be usable yet.
The other labs do the same process, but they don't announce the model until it is about to be released. For some reason Google is announcing at the start of th process.
My guess is Google knows it is (way) behind the and needs to keep drumming up interest. Although at some point it becomes counterproductive (raising "yet another not available model; is it vaporware" vibes).
Didn't Anthropic also announce Mythos at the start of the process, five months before public release?
Creating a false sense of scarcity is essential to get people talking about it. I get almost endless inquiries from peers now that I have access to Mythos.
I don't think you are their target audience, unless you are in their promotions committee or a large holder of their stock.
The target is to make a celebratory announcement.
goog released it just before the earnings call. anthropic and openai don't have these issues.
Eh, maybe I'm too much of an AI safety person, but I'd rather the labs be forced to announce when they are working on large SOTA models like they are a clinical trial. That way if it's never announced they have to say something like "training didn't work out" or "it took over the server farm and we had to burn the hard disks".
hmm, I haven't tried Carbon yet. But I have been using Argon on and off via agent-shell - https://github.com/xenodium/agent-shell and unofficial ACP client.
In my limited usage, it has fixed issues which has not been correctly fixed by sol-6.1 (medium) - https://github.com/auto-gnufied/markdown-modern/commit/a189a...
I am also using it via Google pro tier and did not immediately run into quota issues. But as someone else said in previous discussion of this - Google Pro tier already includes lot of stuff (including Youtube premium etc), the AI plans are just a nice addon.
> For starters, the limits are dreadfully low.
That's the problem for me. Google can have the world's best model; it doesn't matter to me, because I effectively can't use it.
Both Opus 5.5 and Sol 6.1 are extremely good and provide a lot of inference on their $200 plans, and then there are the Chinese models - DeepSeek 4.1 Flash, MiMo, and StepFun all offer a lot of value per cost.
At the moment, I don't see a niche where it makes sense to use Google's models, regardless of how good they are.
In my experience, (using 3.8 flash) the Google models do a fairly good job at summary notes and simple documentation (do this, do that). It doesn't seem to be as bad as Claude for producing headache-inducing text.
3.8 flash is pretty good. it's not expensive, works great for reasoning tasks and it's fast.
for coding .. it works ok but i prefer the openai or anthropic models, much better results.
> I find it difficult to get invested in Gemini because nobody will have access to Carbon for a few months anyways.
I feel like you're being overly dramatic here. Argon was 13 - 15 days.
Argon was announced September 30, made available on October 13 to Ultra everywhere, and Pro in the Gemini App. Pro plans got Argon on October 15 in AGY.
This is the first time they've slow-rolled a model. Who knows how long they'll wait on Carbon.
The Ultra-lite plans ($99/month) get some pretty good quota where you can actually use Argon some more. Maybe Google shouldn't be grouping together plans, but it should also be noted that $20/month also gets you 5TB of storage on Drive. If you paid for Dropbox, you get 3TB for $18/month (without any AI model usage).
(googler, opinions are my own)
If we go back only 45 days, Opus 5.5 was not even out yet. So for more than a third of the current SOTA model's existence, Google's response to it was under its own embargo. When it was finally out, paying users get 3-4 prompts a day, which means Argon will be experienced by a tiny minority of people, another unforced error on Google's side.
By the time Carbon comes out, I fully expect Anthropic, ChatGPT and/or a Chinese lab to have its answer ready to ship in less time than it took Google to approve a release.
Since you're a googler, can you trigger some internal process to improve the connection between google services?
Gemini cannot create "my maps". I like creating a map of stuff for travel and now I ask it to create an importable file (which it doesn't always get right) but it should honestly do that itself.
And I don't mean that from within the Gemini app, I'd like a shareable list of places, which you can do via a very outdated maps UI
>can you trigger some internal process to improve the connection between google services?
You might as well be asking an Adobe employee to bring up improving integration with Canva.
problem is, i don't care about the extra storage at all.
my whole family of 5 people is using in total 160 GB. personally I use about 15 GB
I have 160G of screen captures from Tumblr from my then angsty teenage kid. I think my spouse takes a few Gig of photos for each outing we go on. Several people dress for fancy thing via a process involving many clothes changes and even more selfies.
In my experience with antigravity-cli for coding Argon gets the task finished much faster than 3.8 Flash and with a higher quality output. The quotas on Pro are about 2 hours of usage per week for Argon. Its a really nice model to use. Only thing that is annoying is that it still struggles with tool use on the gemini website.
Same. I subscribed to Gemini pro and requested a refund literally the same day. Asked it to put a technical image on a presentation (gave it the image) and it kept generating a different image of a peaceful landscape... Yeah, very pleasant but totally unrelated.
It's kind of an odd release. Yes, it's technically the top intelligence model by like one point above Claude according to Artificial Analysis, but it's like barely cheaper?
It looks like the best sort of bang for your buck is still GPT Sol and GPT Astra. Claude and Gemini have just been going for that number one intelligence spot by sacrificing a lot of efficiency.
It does sort of show their hands a bit that their larger goals might be outside of just consumer sales but also seeking hyper intelligence that could bring value in new ways of discovery (if it ends up being a legit outlet for such things consistently)
Yeah that "Pro" usage is a joke! I wish google paid more attention to what the people want! it's a shame I loved Gemini 2.5 and 3 when they first came out they were super amazing!
Agreed on the limits, they're quite frustrating. I've still been preferring Argon to Opus 5.5 though, because even though Argon gets details wrong, I find that it's much more creative and willing to explore ideas. In my experience Opus tends to be rather condescending and won't make room for less orthodox ideas to develop. For what I'm doing, I'd much rather have good ideas that I implement mostly by hand rather than regressing to the mean and have the LLM write the code.
>Lastly it's the only "SOTA" model in a long time that has actively hallucinated details. I don't know if it's because the Gemini harness is not asking it to verify information, but I've had some real Deepseek V3-like lies in responses.
I don't know what it is about Google models, but they are the worst at hallucinations. I don't understand how they can so consistently be this bad.
> has actively hallucinated details
Gemini models always suffered from this. They were almost always best in terms of intelligence, but one of the worst to use in practice, because they have a lot of failure modes on simple tasks that simply give factually incorrect answers, or completely break and output gibberish.
I had the same experience. 4 messages on medium triggers the cooldown. The utility isn't really relevant if you're on the Pro plan.
> Lastly it's the only "SOTA" model in a long time that has actively hallucinated details.
Yesterday I used Google AI-Search (so Gemini Flash 3.5?) for opinions on a traffic accident and it continously constructed law-interpretations and then referenced the wrong paragraphs. It talked about rules on road-crossings and cited paragraphs pertaining to alcohol intoxication as sources.
Note that Argon was rolled out for IDEs for people on paid AI Pro on Oct 15/Oct 16 (a couple days after Ultra users), but of course, usage limits are extremely low
I have it on $200 Ultra and it feels like Opus 5.5 (I do not think about limits) rather than gpt-6* models where I constantly hit a wall.
Yeah, I thought it was just me - it hallucinates more than Flash, Flash-lite and Pro.
I have experienced all of this too. I also find Argon still seems to have the sycophancy problem that some of the other labs have stamped out to a large degree.
It is expensive as hell. That said, on my weird personal benchmark (https://botbowlbench.com/) it reliably beats Opus 5.5, which surprised me a fair bit.
It's terrible. I tried it via API in OpenCode. It's so slow, and the lack of reasoning output makes it feel even slower. And I also noticed the lies. I gave it a high-res image of a map to classify labelled locations, and it started going on about how smart it was for the map creator to use squares as the symbol for one of the categories of labelled places, and gave me a list of all the places with squares along with their category, but the map has no squares. It's circles, triangles, and stars.
I am having a very positive experience with Argon: since it was launched I accessed it through Ultragravity and connected via a Google Cloud account. For one month I have been trying to move the needle in SHA256 cryptoanalysis with Claude to not avail and Argon moved "two needles".
Since then I tried it for experimenting on diverse fields. For example, this week there was a discussion here in HN about the non-continuation of Python funding on the JIT, so I "played" again to removing the GIL and moving to the JIT in Python, it did it. I played with many other things, even the Riemann Hypothesis (it just removed their rational parameter rounding only moves 0.875 towards 0.87495702, nothing significant though).
Many other relatively great things were done this week in parallel. I have some budget for research.
> Makes it seamless for trip planning.
Trip planning is the most often used use-case for agents/bots I see in marketing. I'm lucky to travel once a year, but if I did have a trip, I wouldn't feel comfortable letting an LLM take the wheel. Too many variables for wrong flight or room, closed locations in itinerary, etc.
Now, critical server infrastructure? Sure, have at it Claude, make no mistakes!
I would literally never let an AI plan my trip. I do have very specific interests though and it's nice to have an overview of suggestions of places to go.
Plus, it's great at researching the history of places you're visiting, so you can find cultural experiences a bit easier.
I don't travel often, but I do live in Europe where it's easy to visit a new city or country in the weekend. This makes this functionality a quite common use for me.
The best [whatever] is the one that is the most available.
> Lastly it's the only "SOTA" model in a long time that has actively hallucinated details
Could you expand on this? I’ve never seen a frontier model that doesn’t hallucinate details fairly often, what do you mean by “actively” here?
I mean this specifically for general tasks, like personal research. Small stuff. I was asking for espresso machine recommendations and it literally came up with a non-existent machine that supposedly met all my requirements. I've never seen that with ChatGPT, Claude or Kimi. It's quite surprising how it did that _after_ doing a Google search.
Weird, using AGY I get tons of argon and its on a weekly limit.
Argon ran out so fast on the $20 Pro plan that it's practically unusable. I can't imagine how restrictive the limits must be for Carbon.
Doesn't mean jack without access to it.
I used to defend Google's models months ago, but switched to Luna for less intelligent models.
But with this bs of not making it even public, pushing off release of newer models late, I lost faith in Google.
yeah, IMO AA should be excluding unreleased models from their benches or risk becoming an irrelevant marketing platform that no one uses anymore.
It has already become irrelevant to anyone paying attention. Raw scores at published benchmarks mean next to nothing in modern use. They are either gamed to hell or unsolved to the point where differences can be explained by randomness. Speed, cost per token, tokens per task and hallucination levels are the useful axes you can compare along these days if you're not doing scientific frontier level research.
They probably prefer being used by the deep-pocketed organizations that have access to Gemini 4 Carbon even if it means losing the entire rest of the market.
They've only recently emerged as something people reference and now they're already dying.
Yeah. It is vaporware at this stage.
Also, their tooling still is complete shit. I'll not be forced to use Antigravity thing even if it is available and clearly better than Opus or Astra. Their subscription is useless. API can be used with anything you got but that's gonna cost.
Not to mention blocking API usage with subs.
I never use any google models for any agent work any more, in case they block me.
Started migrating gdrive, and gmail to other providers at this point after horror stories in HN, that they lost access to their gmails, etc.
How the fuck can something that was announced less than a day ago be "vaporware".
I have a car that is better than Elon's, it actually does 2 backflips, my friend saw it happen. Will be released soon.
Prove me wrong.
If you're talking about track record, Argon had the same sort of announcement and was released.
It's announced with trust me bro benches, no you can't verify it yourself, this might not even be the model you get.
It's been provided to AA under clandestine circumstances, no you can't verify it yourself, this might not even be the model you get.
People on HN for some reason "wow this thing that I can't use is so great, really excited about all these ads I just looked at"
You should be running your own benchmarks often given the nature of these products. Releasing these models whenever with whatever corresponding benchmarks provides you no assurance that things will stay the same.
Having a great time with an ice cream brand at a store is no assurance against hollowing out the brand tomorrow.
Gemini, for whatever reason, has consistently been the best for explaining scientific concepts for me.
Especially with the recent addition of graphic visualization widgets
It manages to strike the perfect balance between depth and style of prose that other Frontier models just can't quite seem to match
This is the only use case I've found it superior to ChatGPT or Claude for - helping me understand higher level math. It's slightly easier to understand than the other models
Do you have some prompt examples I can run. Thanks
I'll publish a few of my convos
1. Sleep debts effect on muscle size and strength gain
https://share.gemini.google/Gvdb5Q02INrl
2. Fish oil and extra cellular vesicles
https://share.gemini.google/fem9EBCe4mfy
3. Pharmacology question about human-equivalent dose
https://share.gemini.google/RWNYJ2eiNjcU
Not OP, but I asked Gemini 3.8 Flash this question (via self-hosted LibreChat) and got an excellent answer:
Just talk to 3.8 flash about whatever (caveats: ancient knowledge cutoff of jan 2025, small parameter model so if niche '90s korean animated series is your jam, it's gonna be rough). The model is a real joy to talk to, I even will feed it SOTA model output to clean up and clarify for me.
Its the first model ever that I have been worried about a successor losing the "feel" that it has.
Carbon scoring below Opus 5.5 on coding highlights how magnificent Opus 5.5 is as a coding agent. With just a $20/month sub, it performs a ton of work at a very high quality.
The benchmarks of a model that hasn't been released yet are definitely suspicious.
I also think Google should stop "releasing" models that aren't actually available. For their own sake, because by the time Gemini 4 Carbon becomes available, nobody will notice. There won't be a new press release or much excitement around it.
There's an issue with this index where many models are listed in the model chooser, but missing from the index. E.g. Qwen 3.8 Flash Next is listed but missing, as are older Claude (4.6, 4.5, etc) or OpenAI models. This makes it a bit tricky to see the improvements over time.
They removed Qwen Flash Next and GLM Flash from their benchmarks, as of two days ago. They're not publishing any figures at all for them (they show as "N/A").
https://artificialanalysis.ai/models/qwen3-8-flash-next
https://artificialanalysis.ai/models/glm-5-3-flash/
edit to add: It's very disturbing, because these open models (GLM particularly) were among the best of all LLM's on their benchmarks. On the intelligence/cost frontier, specifically. Archive.org remembers that GLM Flash was in their green quadrant just a few days ago, next to Haiku:
https://web.archive.org/web/20261014031624/https://artificia...
It's completely gone now. AAI (as far as I've seen) haven't publicly commented about why they did this.
well if there was any doubt about why openweight models were ranking lower on every iteration of the benchmarks... this should remove all doubt. to just flat out remove is very overt
They both appear today on the chart archived, the one you say they don’t appear on today.
I want to talk about my experience with Argon, noting that I used it via OpenRouter on a Raspberry Pi, spending around $15 in credit.
My experience is that Google is aiming to create a generalist model – but a truly generalist one! In fact, I find it particularly accurate in general terms and even in long conversations, maintaining excellent consistency and a wealth of information in response to complex questions.
I’ve tested it both as a coding agent – though, precisely because of what I mentioned above about its ‘generalism’, I don’t think it measures up to Fable 5.1 or Astra – and I’ve really appreciated its qualities when supervising my agents’ activities. It was able to keep track of them, suggest alternatives, and monitor the entire lengthy process in parallel without ever straying too far from the request or losing the thread – as often happens with Claude and OpenAI (you only need to test it in Claude Code itself, in both Ultracode and the agent team mode – albeit experimental – to realise how, once the task gets underway, both of them lose their way).
Good for them, having a frontier model that nobody can actually use.
It kind of doesn’t make sense. Modern google is typically kind of bad at building products and very good at getting them in customer hands. This is the opposite of that.
It does make sense, when you consider that Google had its earnings report yesterday, and missed its targets. $GOOG is already down 13%. It's an announcement purely for their investors.
I remember when Opus 5.5 came out, we had a discussion about whether it was nerfed a week later [1]. It's not possible to do so with Gemini 4 models since none has been made available the day it is announced.
Without us being able to access Carbon when it is announced, there's no way to know the Carbon we get a few weeks later is the same thing as what has been benchmarked here. I think benchmarks should verify what is benchmarked is exactly the same as what's been released.
Gemini 2.5 flash and 3 flash were highly underrated models that performed way better than the peers and we used the hell out of them.
Since then none of the Google models have competed well with the others at their price points. Long context performance drop, instruction following issues, unnecessarily complex and sloppish outputs.
Argon is no different, it feels just an iteration better than 3.8 flash. I don't trust the AA ranking yet.
I agree. Flash 3.8 is not good and actually quite expensive, given its tendency to overthink everything. We've been transitioning lots of workloads that were formerly on Flash to Haiku 5.5. Great model.
Even with gemini 2.5 or so i remember the models used to just simply hang in production and randomly used to collate tokes and give in the output stream vs giving one by one which was weird.
Also the guardrails were implemented in a very bad manner. By default the models used to raise a default guardrail error on basic queries.
250tk/s is really the sweet spot for chat IMO, results from Flash were fast and usually good quality.
You know what. When Gemini 3.1 Pro Preview came out it was better than Opus at the time. It was my main model for 3 weeks.
Until it got lobotomised. Then it lost most of it's capability.
Similar situation happened to Anthropic's Fable. It was an amazing model until Opus 5.5 came out.
So now, I'm not even looking at a "new" model until it is a month or two old. By then we will know if they will destroy ability to make it cheaper to host.
Since 3 Pro we already know that Google's model are very good in benchmarks, but when you start programming with them... not really good and each model has its quirks that make me continue the project with something else, once I fixed gemini's bugs.
Is this a pro 3.1 situation that by the time ot reached the users it produced no more work than the flash variant or competitor for absurd pricing?
The time between public announcement -> public release seems to be a tacit admission that Google is still a bit behind the frontier labs. Google is justifying the delay by pointing to cyber risk and a closed-access period reserved for analysis of safeguards. I'm dubious of this justification. But if it is true, I'm pretty sure the other labs are doing similar sorts of things in private. I think most of us prefer it that way—if Anthropic public announced Fable 5.5 two weeks ago with no availability that would add to my annoyance. Maybe they learned their lesson with Mythos, or maybe it's just that Google also does not have an IPO looming. Who knows?
I guess it's also because the model is available to at least one group, and this releases embargo on information about it.
I tried Argon for a large historical HTR transcription project recently, since I heard it was really good at this. It was really good, but like all top US models I've used it was
* Definitively very good at domain specific knowledge. It can read sloppy 19th century danish gothic handwriting with faded ink just fine. Not perfectly, but probably better than I could have done with a day of struggle for every page.
* Expensive.
* Bad at actually doing what I said. I had told it in the prompt to be careful not to miss text, but I hadn't explicitly told it that some images may have text in double-column layout. So on those images - over half of my 300-page document - it produced an excellent transcription of the first column, and then considered itself done. Want to try again with a more careful prompt? That'll be another $20.
For ocr, you have to practice, practice, practice with your prompts on small sample sizes before one-shotting a book. I create a json schema for the output that describes the structure in detail (using ai from my prose descriptions of structure of course). I have specific tough pages I use on openrouter to test every new model I am interested in. Gemini has and does absolutely dominate for this. But flash can be better because it doesn't overthink things.
I did do test images, but apparently not enough. It's not 100% of images it drops the second column on either. On many it gets both, on some it only gets the second column.
I also found that it ignores other instructions sporadically ("Don't use letter variants or ligatures in the output, use the normal Danish/Norwegian alphabet when at all possible", still a few Unicode tall s'es in the output.)
It's good, but it's so frustrating since "worse" models manage to follow such instructions much better.
> That'll be another $20.
That seems arguably pretty cheap compared to the human alternatives.
I do get super annoyed at how specific you've got to be with these tools. They are like almost like malicious compliance geniuses lol.
> They are like almost like malicious compliance geniuses lol.
They're like a monkey's paw or evil genie I think.
You'll get exactly what you ask for, but lots of weirdness you didn't expect.
To be fair to the model makers, deciding what to do with an under-specified prompt is hard, particularly in an RL environment where you can't just ask the user.
For stuff I want to run for a while, I'm defaulting to telling it to ask me the questions upfront to reduce the incidence of these kinds of problems.
Just so everyone is aware of the "coincidences" that happen with this index:
- Two days ago AA announced their v5 Index which added a few new benchmarks and tweaked a few things.
- Today the newest model announced from a big lab tops the charts.
I'm not saying that AA is definitely taking money from the big labs and changing the benchmark to make the labs' new models look better, but it kind of looks that way. This pattern of behavior has happened before, where the index gets tweaked right around when a new model comes out, and the new model is on top. AA does not, AFAIK, provide a way to see how the new models would have scored under the older index versions. You could probably calculate it yourself, but I'm not going to do that much legwork just for an HN comment.
It's interesting because they publish the index methodology, so you can't really accuse them of not being transparent, but I don't really believe that the choices to update the index were completely independent of the model they happened to be evaluating at the time.
Related: The DXOMark camera scoring method also had similar behavior, where they would release new testing methodology right before flagship smartphones were released. Again, they are technically being transparent about the process, but it kind of smells like the "independent" testers may not be as independent as the average user would hope.
I had a look at the changes and the biggest impact seems to be from adding Terminal-Bench-science 0.1 and having it contribute 15% to the overall score.
Example problems are:
- https://hub.harborframework.com/tasks/terminal-bench-science...
- https://hub.harborframework.com/tasks/terminal-bench-science...
I have no doubt that these are very relevant task for people in those respective fields, but I suspect they have next to no relevance to some 99.9% of model users. Hence why especially smaller labs with smaller models didn't really train for such use cases and you can see it.
Personally, it's not something that matters at all to me, as I don't work in cheminformatics or bioinformatics.
This is also arguably more of a test of a model's knowledge base than reasoning ability.
But most importantly, there is also the question to which extent the aggregate score then remains a meaningful result when you mix up too many too disparate benchmarks.
The coding agents subindex, in contrast, looks at least superficially plausible [1].
[1] https://artificialanalysis.ai/agents/coding-agents#coding-ag...
Ironically coding has no relevance to something like 95% of users (I forget the exact OAI statistic), but it is the mainstay LLM benchmark.
True, but coding is where something like 80%-90% of their revenue comes from; few other use cases are as token-hungry, and none of those are nearly as widespread. Many users will of course use the models just as chatbots, but they don't generate much in terms of revenue. And that is ultimately what determines where labs focus their resources.
Yeah, it is very suspicious. Each time they update their ranking algorithm, the closed models from US labs jump up and any previously high ranking open model jumps down. It happened with MiMo, Kimi, GLM. All were right there amongst the very top, and each time that happened, AA followed quickly with an index update that shunted them dramatically lower.
Check out vals.ai for an alternative. Not sure how independent they really are either, but it's at least good for a cross reference.
I also look at the ECI from Epoch.ai as well, but they haven’t evaluated Carbon yet. Probably because the model isn’t widely available yet.
Have you considered the other direction? They test a new model, and realize their current index is broken, so they improve it?
At the previous iterations they were accused of favoring OpenAI. Now they are accused of favoring Google.
We’re literally talking about the same thing, but ascribing different motivations.
I do think the test a new model and realize their index is broken- the new model isn’t on top, so they change the weights to make sure it’s on top.
The difference is that you seem to think they are doing so out of some innocent feeling that the new model is actually better, while I think they are doing so because they were paid to do so. I think my interpretation is more likely, but that’s just me.
So explain why the Chinese are not paying to put their model on top, surely that would drive a shit ton of business to them.
Or are you implying that the Chinese can't afford the amounts paid by OpenAI/Google.
And how do they realize their current index is broken? They either have some recency bias, or indeed favor the big American labs (more likely, since a new Chinese model topping the charts triggers a shakeup).
It's odd because I wonder if anybody actually cares about such scores. It's not like millions of end users look at the score and use it to make a decision what to buy. Subscriptions can easiliy be canceled and people anyway use the models they "feel" work best for them. Hardly anybody I know uses an even remotely scientific method to evaluate model performance. It's mostly vibes with a little bit of (mostly flawed) A/B testing sprinkled in.
So ... why bother to cheat?
> So ... why bother to cheat?
I think part of it is to justify capex. "Yeah, we spent x billions on this, but look, we have the best models, we're beating OpenAI and Anthropic, we're winning, it's all worth it!"
From all of the terrible benchmarks of AIs, the AA one is the least terrible.
My paranoid impression was more that the updating and addition of tests — obviously essential in this game — was delayed to provide advertisement for Kimi K3.1. The same happened for K3 — and this is why it was famous — but its position had collapsed by the time of 3.1
They can release even Jambon and Jargon, why should I care when I cannot test it?
Creating the hype
This is just a hunch since I have not used Argon very much, and I have not used it for coding (deepseek 4.1 flash 1017 with dsh, and qwen 3.8 max are so good for coding tasks that local models have difficulty with).
My hunch is that Google will end up being best for non coding tasks. Google can concede coding to other vendors who pay Google for infra.
At this point frontier models are good enough to be a pair programmer. But only OAI and Anthropic offer good limits. Maybe they're burning money but if the Google limits are the future of usage style accounts then we all have to get used to API
Don't bet against Google
The situation with Google is a bit unexpected.
They have top of the line research, I mean, they invented the thing, and they are still doing stuff that goes beyond making a bigger LLM, as it seems to be the only thing the others are doing, research-wise.
They also have hardware capabilities no one else has, they invented the TPUs, and have lots of them.
They also have the brand recognition, ecosystem, user base and lots of money.
So why are they lagging behind on the actual products, and by lagging behind? I mean they are always in the position where they are just behind the frontier, but still in the game.
It seems almost deliberate. Maybe they are playing the long game, waiting for the bubble to burst. Maybe they don't want to compete against the more profitable parts of the company. Or maybe their researchers are not interested in making an actual product unless being forced to.
People always love to think the AI race is a duopoly (OpenAI vs. Anthropic), but from what I have experienced, Gemini was always holding on its own, and I find myself using it more than Claude.
True, I use LLMs as glorified search engines to unearth material to read myself, but Gemini is much more useful if you decide to learn yourself. It also offers interesting expansions to your questions.
While I don't offload my work to LLMs (e.g.: Write this project, I'll be watching TV), I find them useful for closing my knowledge gap by collating information, and Google's Gemini is good at that.
Gemini is just too expensive for what you describe. Their 20$ plan only gives you access to the free tier model
I have Gemini because of my Google One membership. I already was on their 2TB plan and it gave me Pro level, IIRC, and it was generous. Now I'm on Ultra mostly because of Google Drive storage I get, but Gemini also gets a nice boost, as well.
I'm on $20 Claude plan, and it's also ample for my needs, for now.
I think this is because of capacity issues. Higher paying per token users probably get preferential capacity allocations to those on monthly plans. The allowance for what you get in the monthly plan increases as the models age and the likely capacity problems improve.
The $20 plan gives you ~120 minutes of high thinking time from Argon weekly. Thinking time isn't an exact metric, context size matters a lot, but I have been using it on the $20 and still have 25% left with ~85 minutes of thinking time on high for a project I have been working on.
Thanks David Guetta!
They have an insane amount of resources but are so bloated, have a ton of bureaucracy, and have lost a lot of their top talent. Looks like they have figured things out now though.
A lot of people do though by looking at the current stock price.
Never bet against their contempt for paying customers.
Really? Been 3 years since ChatGPT and Google still going from misery to another in their AI products.
Even if these numbers are correct, they don’t have any useful product for coding or search. Not sure what you’re referring to
Not everything is writing code and search. My uncle works in mortgages and the (very large) firm he works for is entirely Gemini. The way he talks about it is with wonderment in his eyes while he goes into detail on how it went through multiple documents and found unaccounted for cases. I think Google is doing fine in these kinds of industries.
I wouldn't even bet that Google is better than OpenAI and Anthropic for these categories, but they seem to be well used outside of our direct space.
It worked for Microsoft with cloud. Existing industry penetration goes a long way.
Artificial Analysis is not trustworthy anymore. Every time an open-weight model, especially Chinese, looks to be nearing the top, AA updates the index to (ostensibly) specifically push closed models higher. Just recently with v5, OpenAI models were pushed up.
I don't think that's the right read. Deepseek Flash 4.1 1017 did not get affected much.
I think what's happening is Chines models genuinely try to benchmax on it and hence they suffer when a new version comes out.
> I think what's happening is Chines models genuinely try to benchmax on it and hence they suffer when a new version comes out.
I read somewhere on Substack that a lot of this was driven by the inclusion of more knowledge work benchmarks, where the US labs are stronger, versus coding which is where most Chinese models appear to put their energies for now.
Or it could be that the benchmaxxed models are getting pushed down by the introduction of unsaturated benchmarks. Muse Wonder also went down 52 -> 43 after the update.
It's not that hard to create your own uncontaminated eval for the problems you care about, and compare.
Here's mine for coding in Rust, and I definitely see the same pattern of "most chinese models do much worse than on public evals that have been around long enough to train on" that AA v5 surfaces: https://slopcop.com/power-ranking
Don't care, it's not released so in reality it's undefined, not #1
I haven’t tried Gemini for coding yet. I did consider buying their subscription, but based on what I’ve seen from other forums, Gemini has never been a frontier in coding, even with good “benchmaxing”.
Let’s see, maybe they’ll surprise this time.
I have a fairly narrow use case: I'm developing apps in Dart/Flutter. Gemini works well for that.
Boggles my mind that they still offer 3.1. Absolutely 0 reason to use it when 3.8 Flash is better in every respect.
Nice coverup for the Q3 results. Wall St. don't give a F*
why do i not see as much traction and stirring up on the internet for gemini models as much as claude or gpt even though on bench's they are very much THE frontier. is the reason very limited access early or or just not enough publicity or hype as the other labs do?
>is the reason very limited access early
I mean, that's the main reason. How would you expect to see the kind of hype that Claude or GPT can generate when nobody can use it? The hype of those models are primarily generated from people using them to build impressive things and share those results. Can't do that with an unreleased model, right?
Beyond that, it seems a lot of people have learned that these agent leaderboards really don't tell the whole story. They're a good litmus test, per se, and there's plenty of hype being generated around these scores as-is. But anybody using AI in practice knows that benchmarks can only say so much, and one model scoring better than another doesn't necessarily imply that that model is actually better in the ways those people care about. You can see that in this thread as people are pointing out that even these benchmarks seem to suggest that Opus 5.5 is still leading in coding (which is what a lot of people, especially on HN, ultimately care about).
>just not enough publicity or hype as the other labs do?
Well, it's effectively both. Google is certainly not that pressed to generate as much hype as these other companies. They can afford to take their time. It's also worth noting that Google is definitely targeting different consumers, investors, etc., so their strategy will definitely be different.
For what it's worth, I've been using Argon since it's been available in Cursor and I really like it (at least at its current price). I think Google really did close the gap a meaningful amount (maybe not all the way, but enough to prove they're still in the game). Carbon being significantly better while being the same cost is pretty exciting to me. But until I can use it, I don't really care about it.
Google has to get it's shit together. All the stats and charts doesn't mean squat because when I try it now on a provider all I get is trash :(. Makes me question these metrics entirely and really makes me question the authority that google used to perceivably have.
I don’t care and in my opinion AA does a disservice to their users by allowing such blatant manipulation. What would happen if every AI company were to include their unreleased models like this? Put the unreleased models on a separate page and leave the headline benchmark rankings for models that you can actually use.
AA (like most other VC-funded benchmark sites) is pay-to-play.
Want a private benchmark and see where you'd rank? $$$.
Want to show up day 0? $$$$.
Want to show up day -0? $$$$$.
What the AA charts say is irrelevant to me.
Even Haiku is better than Grok
It's unobtanium so nobody should care about it. Any frontier AI company can nowadays create models with ridiculous resource and token usage that will get extremely high scores, but they're of no use when you can't use them.
I take this opportunity to give feedback on Argon. The limitations are a problem. I have a Pro subscription and Argon already stops working after 3-4 prompts with long delays afterwards. It's virtually useless right now even when you pay monthly for it. It is better for some tasks than 3.1 Pro, though. Not much in my experience but it can sometimes fix errors that 3.1 has problems with. I never use Flash models since they often give abysmal results.
So I'm stuck with using Gemini Pro 3.1 for now.
I use it purely for finding stuff in text documents and OCR, at which it excels, but I've found that for any kind of analysis it's some bewildering mixture of smug, defensive, paranoid, cheerful, and wrong about everything.
I feel like the headline here is "the Artificial Analysis index is becoming an increasingly poor measure of capability, having previously been quite good".
I have pro account and previous model "Argon" still not available on my account.
I have it on both web and agy, but you know when you wait for something and in the end it turns out to be not that good...
Mine showed up after clearing cache for some reason.
is it on web interface or antigravity ?
gemini.google.com (Pro plan).
AGY never even update often, and only has gemini 3.8 flash (for Google model).
How can one access Carbon? I only see Argon via gemini.google.com
Is this API-only or US-only for now?
It’s available only to those who read the announcement.
My ignorance laid bare
https://blog.google/innovation-and-ai/models-and-research/ge...
"We're taking a deliberate approach to rollout and are actively engaged in the U.S. government’s voluntary process for pre-release model testing. Starting this week, we will make Carbon available to a subset of cyber defenders and will gradually phase access to additional trusted partners through our Fairwind Program. We’re continuing to gather feedback and iterate on guardrails before making Carbon available to developers, businesses, and consumers via our product surfaces as soon as possible."
These benchmarks and rankings seem more noise than signal these days. They're uniformly divorced from sincerely-attested real world experience. And the real world experience isn't driving any consensus either.
So here's a meta-benchmark: at what point does the act of choosing an LLM product for a reasoning task become less reliable (in the sense of "predictive of future success") than hiring a human being for that same task? Have we already cross that threshold? I think we might have.
And once we do... what happens then? Will the truly elite models be hidden in a sea of mediocrities simply because the goofball "managers" doing the hiring are too dumb to recognize their genius?
By the time this model is available for public use I'd imagine it won't be #1 anymore, which is pretty sad. Even when Google gets back on the ball they seem to find a way to fuck it up.
I couldn't care less, honestly
owaoo
well, $GOOG is down 13%...
slick
A secret model I trained last afternoon is the actual #1 on benchmarks.
No, you can't use it. You can't even see it, and I won't provide you any information. But you must trust me that I am the genius who made the best model in the whole world.
Spare me the celebration. Artificial Analysis should not be granting any company the favor of a #1 ranking for a model that isn't released to the public.
Google's model release is pure PR puffery. It's no coincidence that it was released on the day of its earnings call.
And i guess people dont care by google releases anymore
Argon did not leave a mark or change anything
Why would anyone care about carbon as well
Sunder quoted their tweet in his release announcement. Like that was the main thing he wanted to say.
Of course he would, he paid a lot for the privilege.