Comment by HSO
15 days ago
> I'll be using this for everything that isn't coding from now on.
why? is it not so good on that? or is there something better performance, or better price for same performance?
15 days ago
> I'll be using this for everything that isn't coding from now on.
why? is it not so good on that? or is there something better performance, or better price for same performance?
I'm not the poster you responded to, but I can tell you that historically the Gemini models have lagged behind Anthropic (the clear leader) and OpenAI's best models where coding in particular is concerned. Opus 5.5 is, right now, the consensus best coding model.
That said, I'm extremely impressed with Argon thus far. I take back everything bad I've ever said about their AI strategy. Argon is very good and very fast. It might be competitive at coding, but it's too early to say.
Opus 5.5 medium is a real sweet spot for many many things. But. I got an unexpected refusal (for help creating a browser console script to convert a web-based streaming video to an offline-ready .mp4), which Opus 5.5 low happily provided.
Since Google owns YouTube, this refusal by Gemini seems suspiciously too aligned with their interests. Just a conspiracy theory, though :)
5 replies →
I completely agree; I was really surprised to find that Claude Code Opus 5.5 is significantly better. I had spent quite a bit of time using Gemini Pro for coding tasks, but when I revisited the code analysis using Opus 5.5, it revealed quite a few shortcomings in Gemini's understanding... I code using Python, which is considered the best language for writing code via LLMs (I am referring to linguistic entropy).
Opus 5.5 routinely finds tons of bugs in code that Opus 5.5 wrote, so this may not reflect a difference in model capability.
Sounds like you were using the older Gemini 3.1 Pro from February, and not the new release this post is about
I am using it via OpenRouter for going through some Vulkan code. It's a beast - it has no hesitation putting in instrumentation within the code (having a number of render passes) to dump the framebuffer to PNG files and doing pixel-by-pixel comparisons, putting in false colors in shaders to identify bugs etc. Very impressive.
That’s something Opus can also do. Perhaps by coincidence I also recently debugged shader bugs where Opus dumped the resulting render to PNGs and then using Python PIL to do comparisons. It purposefully added false colors too.
Suspect there is a training set going around focused on comparing and extracting data in distinct steps from image input. Saw it first on Opus 5 on a backpack construction task to extract and compensate for a reference tape being slightly offset in a LIDAR scan, followed by heat maps for per pixel comparison between the reference and blender render. Opus 5.5 did go a step further in the same, extrapolating offsets to compensate for capture inconsistencies. Some may not even notice this happening as Claude Code steers the model to use the scratchpad hiding much of this work.
Found this especially impressive because backpack material related research has been something I know models can still get caught up on and the models being decent at web research in coding nowadays does absolutely not apply to these task equally Recommending nylon canvas shell suppliers or waxed cotton when PVC coated cotton is explicitly request, that sort of thing. While not perfect in reading coding docs, models are far better there.
Like with front end and code “parsability”, feel like you can very clearly point at which labs use what training set, with many often sharing the same suppliers. Once I noticed that, I became very bullish on specific training sets over emergence as the source for current gains.
Out of curiosity, which harness do you use for this kind of task, and how do you sandbox it? I used Aider before, and consider switching to a more recent tool.
I started out with agy CLI but it's horrible because of its very indeterminate context compaction. But I live with it because it's the only way to use Google's subscription. I was and still use Opencode in parallel (accessing Openrouter ZDR endpoints) when I run out of rate limits / weekly limits.
Over the past two weeks, I have started using a locally modified version of deepseek-harness (modifications include disabling telemetry and querying a provider's model list dynamically through Openrouter, instead of relying on the pre-packaged pi-ai manifest that comes with the base code). So far, that has been the best experience - I really like the caching, tokens/sec stats that it provides. (EDIT: I don't know a lick of TypeScript but AI-driven modification of the harness is good enough for me to make these tweaks).
Sandboxing is a definite issue for me. As you perhaps know already, headless operation is often not an option in graphics/game programming which requires actual render-surface instantiations from windowing systems and then input-context handling (keyboard/mouse/gamepad) as well. So I run most development on a VM. But part of my test-suite and smoke-tests rely on runninng it directly on the host OS (which is not ideal). I'd love to hear suggestions to avoid this.
3 replies →
Inexplicably, despite the fact that I pay Google actual money for an AI plan, they don't want me to use their latest model. Instead, I'm allowed to use the competition (Opus and Sonnet 5.5). I don't think it makes sense but what do I know?
I think the rollout was phased. I couldn't see Argon in Antigravity on my personal AI Pro account until late last night.
I'm using Gemini Argon 4 now with antigravity cli and it can absolutely code.
When does it auto compact? Is it at 250k tokens as for gemini-3.8-flash? If it's more generous I might consider upgrading to the ultra plan.
it has a context of 1 million tokens. Antigravity classifies the context which is helpful.
do you have ultra plan? it says regular sub doesn't have it.
i'm using our companies enterprise account.
> I haven't tried it for coding yet