43 comments

[ 3.2 ms ] story [ 42.2 ms ] thread
Tried at work , this release def a moment I will remember. My work is not the same . The model is the first model that offer exactly as I want :

For hard tasks , that needs precision I will wait and pay expensive tokens

For everything else , query data , logs, rolling out releases , I’m using grok and it’s much better vs other tools and much cheaper too .

Why not wait one more day for GPT-5.6?
Well, I'm probably not on the list of special people who will get to see GPT-5.6 Terra.
I am 99% sure the post was written by AI
Either that or a human that has started writing like an LLM, having been "trained" on LLM output itself by sufficient exposure.
I'll actually put in spelling errors and grammar mistakes intentionally these days to show human
> Role reversal, two figures, one file.

> “snappy stylist”

Funny you can tell its slop just by this

Barring the retry thing, n=1 on all models? Am I misreading, or is this a joke?

Variance in quality on these things is so, so high.

So strange to write a whole post with Claude giving the best results and Grok consistently the worst, but awarding Grok the winner because at least it did the worst fastest?
I tried to one-shot the first test (the Rubik's Cube test) with LucidQuery's Swift model, to test it, as there are not much benchmarks about it and that they brag a lot about it, and I was pleasantly surprised to see it achieving a result similar to Grok 4.5 but in one shot (there is the same issue that if you scramble twice the solve button does not work anymore, but it got it in one shot).

Though it crunched most of the free quota, 47111 tokens, so I couldn't make multiple attempts.

Love the idea, I think more complex games would show the gap in ability better.

Do it again but this time get them to make a multiplayer online Jetmen REVIVAL game. Online play is key, because it's very complex. Jetmen is a good game for this since it has physics and customization that's complex enough but still simple.

Too nice to Grok, if there are really cost savings it should say how much each of the three demos cost so we can judge if it's worth the lower quality (probably not). The time to complete each would also be interesting.
I'd like to see the comparisons with DeepSeek, Qwen, Mimo, Kimi and GLM
Interesting that all four models converge on such similar designs, for such short prompts.
[flagged]
> This feels like a kid trying to do science. The will is there, but lacks experience.

It's funny, when I saw the title I was hoping the article would include some sort of blind ranking, where you could see the outputs (without knowing which model they came from) and score them on some criteria. Could have been a fun way to get a better ranking of the results.

>Comparison are completely subjective

Nothing wrong with that.

In this case, the requirement is clear enough, and the result is similar enough to judge it subjectively.

Even code-wise, if tests pass and the features are there in all cases, the rest of what matters (architecture, code quality, style, readability) is all subjective too.

GPT somehow wins the particle sandbox thing too despite its heavy attractors not attracting anything.
> This feels like a kid trying to do science.

lol. These are the comments that keep bringing me back here. Great feedback delivered with a dash (or more) of salt.

You broke the HN guidelines badly with this, first because of the name-calling and personal attack, and second because it is a shallow dismissal in exactly the sense we ask people not to post here:

"Please don't post shallow dismissals, especially of other people's work. A good critical comment teaches us something." - https://news.ycombinator.com/newsguidelines.html

On the plus side, your comment does contain some specific observations which could have made for a good comment—one that communicates interesting information respectfully. If you'd please post that way in the future, we'd appreciate it.

Isn’t the number of turns most important? Some agents take repeated input, while others can mostly one-shot what I’m looking for.
Chat got ones were slow on Firefox mobile
This is disgustingly biased. The conclusion is that Grok holds its own?! There was zero evidence of that.
Yes, I wonder how the verdicts would hold under a blinded test. This analysis read like the authors going out of their way to be supportive of Grok.
I have not used grok 4.5 yet, but the other pictures match my experience doing anything graphical with the other models that it cracks me up. gpt 5.5 has no design sense whatsoever. It cannot even make terminal output not look terrible. I've asked it to use colors and formatting in various ways and got goofy randomly colored output. opus 4.7 and later seemed to have an inuitive design sense by comparison - 2d or 3d. Fabel 5 is just rock solid.

Yes, subjective. But it matches my repeated experiences with these models for what it is worth.

I get better results with Opus than Fable 5 on various oneshots (including our old friend of "generate an SVG of a pelican riding a bicycle"). (Opus is also far and away better than pretty much any other SOTA or near-SOTA model.)
“The honest headline:”

Written by Claude. Ugh. If it’s worth publishing, it’s worth proofreading, folks.

> The receipts: speed and cost

I don't get why cost per reply is at all relevant here?

Why do so few who attempt comparisons actually compare dollars per task.

I get the point of this demo but if instructions are clear, tech stack related resources are available, then the models do not differ as much.

I use different models all the time. And mostly lower cost ones. I do not know how people write software these days, but I have clean instructions, usually in Epics and they have Tasks.

I have been using DeepSeek V4 Flash for much of my coding in https://github.com/brainless/akar for example. Planning is mostly done by Qwen latest (in opencode) or Sonnet.

For my commercial, client work I use Claude but barely use Opus. Sonnet does most of the work. For a recent project, I went through a 35 page PRD in about 4 weeks, that includes client calls, changes, Ecpi/Task generation, a massive test suite, deployment.

If you like this kind of comparison, we have an arena of 52 apps one-shotted across 21 models here: https://arena.logic.inc/

I keep it pretty up to date (tomorrow Grok 4.5 and Sonnet 5 should be pushed).

Could probably do this with a much older model given that it's something that probably has thousands of github repositories for source code to do so.
I’m spending a significant portion of my day waiting for agents to execute.

What’s more interesting to me than time-to-first token or latency is the time it takes for the agent to execute, from starts to finish, excluding when it’s waiting on a human.

Half year ago I tried to use Codex, Claude and Gemini build the same scripts to automate various things on my machine. Claude was the clear winner back then, making the most reasonable assumptions, presenting results in the easiest-to-read format, writing runnable script with minimum dependency. Half year later I think Codex and Claude models have both advanced a lot, but Gemini is still lackluster. Gemini could catch problems when reviewing Claude/Codex's design plans and code, but it's hard to make Gemini make complex plans or implement complex code by itself.
Grok failed the Rubik's cube. I pressed Scramble twice and then solve and it didn't solve the cube. Opus did.
>look guys, we burned money! Upvote pls.