Comment by nater5000
4 hours ago
For what it's worth: Argon is a pretty good model, and this is coming from someone who just sticks with Opus 5.5 mostly across the board. For the current introductory price, it provides an exceptional value. Looks like they're trying to release Carbon (which is apparently a significant improvement) at the same price as Argon, which would be a crazy value.
It's worth trying if you have easy access to it (we use Cursor at work, so it was just a matter of picking a different model for me). Don't know if I'd go out of my way to get a Google AI subscription for it, but if Carbon ends up meeting these expectations, then it may be worth doing so.
It's important to note that Argon works best on Antigravity Harness: https://x.com/wenhaocha1/status/2114559544156205413
It's best to start with a relatively clean GEMINI.md too. Many configs optimized for Claude doesn't work well because Argon didn't have those same failure modes.
I've just renamed my files from CLAUDE.md to AGENTS.md I certainly won't do that again regressing back in the vendor specific direction lol
This would make sense. In our local coding agent battle system, Argon is tanking, and this is running on opencode, importing agents.md and claude.md.
claude.md is not needed anymore btw, claude now reads agents.md if it doesn't find the other.
2 replies →
I find their products confusing as usual. Does Antigravity sub work same as $20 Codex? Are the limits somewhat similar to ChatGPT and Claude?
We're working on a battle system for local coding agents [1] and Argon is really bad. Literally the worst model in our initial ranking, and Deepseek Flash, Muse Wonder, Grok are all in there.
Top is Opus 5.5, followed by Fable.
[1] https://github.com/bottomless/agent-duel
That doesn't seem to match the arena.ai rankings, who I'm assuming has a far larger dataset of rankings than you currently hold.
https://arena.ai/leaderboard
You're right Arena.ai has far more data. Our data is actual local coding agent head-to-head battles, so I think our quality is far higher.
Their agents leaderboard is literally just randomizing the agent and looking at metadata like tool call errors. In my opinion, it's poor quality data in high volume.
Their web dev leaderboard is in cloud containers, most people don't run agents like that.
I ran a statistical test on our data. Deepseek vs. Argon. Posterior probability DeepSeek 4.1 Flash is stronger: 99.1%.
2 replies →
I've used argon via `agy` cli tool and was not impressed at all. However, I decided to burn up the remainder of my ultra credits on a visual reasoning pet project.
Argon in low and medium mode had higher quality results than it did when running in high mode, almost every time. My tasks involved the agent finding some details in a raster image and then mark it up with predictions about what it found.
Argon on high would do the work, and then a whole bunch of other stuff i did not ask for. All that extra broke everything else downstream from the analysis.
However, doing the same work with Argon in low effort was on par with results from Haiku 5.5 (xhigh) and GPT-6.1-Terra (medium). So, Argon low works better than Argon high, but for my tasks -- a very weak model relative to how google positions it.
I'm ready for Geimini Unobtanium!
Okay, this is interesting. We are hardcoding the effort (to improve data concentration), and Argon is hardcoded to "high".
Well, my perspective is somewhat narrow (I use it primarily for software engineering and pretty technical data engineering work), so it's possible that Argon is well-suited for the work I do but not for other tasks. I suppose it's just more data points to consider.
Our data is all software engineering run via local coding agents, but yeah your specific use case could be one where Argon is stronger. (Or your personal preference.)
This does not mesh with other battles like Arena where Argon is nearer to the top.
Yeah, we are doing something different and actually running parallel local coding agents head to head, something Arena doesn't do.
> local coding agents
what does "local" coding agents mean? Surely you're not hosting it..
Yeah, this is a new project so help me out here. I mean that the harness is running locally. I'm trying to distinguish this from arena.ai webdev arena, where they run the agent in a cloud container.
my anecdotal experience is that argon and muse wonder full are both a full tier below opus/sol.
So far in our data, there's no difference between Wonder and Sol 6.1. This is with wide error bars, as we're just getting started. Note this is Wonder, not Full as it's not on openrouter yet.
But yes, Opus is a tier above Wonder and Argon with very high confidence.
Argon is the best writing model that's been released in a while
It's sad to see Carbon releasing at the same pricing because that implies Google is planning to do the thing everyone is doing: release promising model for subjective preference, RL-maxx a V2, replace promising V1 with V2 because it benchmarks better
Muse did it, Kimi did it, Deepseek did it, Tencent did it. No one seems to care abojt subjective preference anymore.
Argon is easily the worst model I've tried this year. From all the discourse I've seen, that seems to be the general consensus.
This might be the first comment I've ever seen saying something nice about the model.
Haven’t tried opus 5, sol 6 or haiku 4.5 I see