23 comments

  • HeavyStorm 3 hours ago
    Excellent idea, most terrible execution. Comparison are completely subjective, problem space is too simplistic for today's AI, the resultstable simply ignores that a face isn't a cube (therefore, gpt 5 shouldn't have 100% success) and the retry is uneven. Also, given the random nature of AI, sampling once each model isn't very scientific.

    This feels like a kid trying to do science. The will is there, but lacks experience.

    • sinuhe69 2 hours ago
      It said “3D-looking Rubrik cube”. Maybe your cube looks different but I’m pretty sure for everyone else, the GPT result doesn’t look like a 3D-looking Rubrik cube.
    • hyperhello 2 hours ago
      It’s still science if you say “this appears to be a specimen of X” even if you don’t do a genetic test. Things don’t automatically graduate to science either by repetition or by formal verification. What makes a rubics cube is obvious enough that you can pass or fail.
    • looksjjhg 1 hour ago
      Show us how it’s done then, talk is cheap
  • wwind123 37 minutes ago
    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.
  • dadoum 3 hours ago
    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.

  • jeffgreco 3 hours ago
    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?
    • singingtoday 3 hours ago
      GPT was the worst on the Rubik's cube
      • cuvinny 2 hours ago
        They gave grok 2nd try on that one. Now one shotting a webpage is a dumb metric but if that is what you are testing it did the worse.
      • GaggiX 3 hours ago
        Grok did not render anything, they had to prompt it again.
  • mlmonkey 4 hours ago
    I am 99% sure the post was written by AI
    • ks2048 2 hours ago
      Blog post idea:

      We made Grok 4.5, GPT-5.5, and Claude write a blog post about using Grok 4.5, GPT-5.5, and Claude to build the same apps.

    • jszymborski 3 hours ago
      The honest takeaway: this is 100% written by an LLM.
      • mlmonkey 3 hours ago
        That was the honest giveaway ... :-D
        • Crisco 2 hours ago
          I did a quick skim and the usage of phrases like "snappy stylist" and "speed-and-value monster" were what instantly stuck out to me as AI. I decided I probably didn't need to actually read the article after that.
          • walrus01 2 hours ago
            This is the real unlock of the speed and value monster.

            I am trying to figure out how many LLM converged on a writing style that resembles a LinkedIn MBA true believer. Maybe because there was just such a sheer mass of corporate-speak drone writing out there in the wild in the training data set?

            But more seriously, is there a firefox extension that 'skims' the text body content of a page and puts some kind of "this was probably written by AI" meter, gauge, number or indicator in the top menu bar adjacent to the URL bar? It could even be color coded in various shades from green, yellow, orange, red. If there isn't, it sure seems like something that would be good to have.

            • hattmall 1 hour ago
              It's kinda logical. Most people, individually, have a somewhat unique writing style. So if there's one set of writing that's very formulaic and consistent and you build an averaging machine it's going to converge on that formulaic style because everyone else's writing style is going to be much closer to n=1.
              • red75prime 9 minutes ago
                Kenyans who provided the data for RLHF liked that style. That's the most of it. And a transformer is not an "averaging machine", it's a prediction machine.
              • somenameforme 51 minutes ago
                I'd expect that most corporate speak made it past their data curation, while normal people speaking normally was probably scrutinized a bit more heavily. The PC stuff is also probably quite terrified of a lot of adjectives. For instance I just used normal as an adjective, and that can be a hyper-loaded term if somebody's obsessed with trying to interpret things in the most absurdly bad faith way imaginable. By contrast corporate speak tends to have obnoxious lingo, but lingo that can't really be spun too much. Even for one of those guys, mental gymnasticing 'snappy' into being a secret dog whistle's going to be pretty hard.
    • kristopolous 23 minutes ago
      I'll actually put in spelling errors and grammar mistakes intentionally these days to show human
    • userbinator 44 minutes ago
      Either that or a human that has started writing like an LLM, having been "trained" on LLM output itself by sufficient exposure.
    • dwa3592 3 hours ago
      i will give you the remaining 1% because i felt the same way.
    • walrus01 2 hours ago
      But just think of the amazing advancements over the past 12-18 months in fully automated slop-posting! We've reached a new high water mark.
  • owenbrown 38 minutes ago
    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.

  • steve-atx-7600 2 hours ago
    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.

  • sgk284 43 minutes ago
    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).

    • kristopolous 25 minutes ago
      I want this with smaller models as well like Gemma 4 or Qwen 3.6
      • sgk284 14 minutes ago
        Awesome - will work on getting those in.
  • dirteater_ 54 minutes ago
    > 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.

    • NewJazz 36 minutes ago
      I think these were all one shots, so it was 1 reply per task?
    • baxtr 47 minutes ago
      Tokens per task might be the better choice
      • unanonymousanon 42 minutes ago
        Could you elaborate on why tokens over dollars as a metric?
      • Computer0 43 minutes ago
        Why do I care how many tokens were used? 50,000 or 5,000,000 all I care about is the output quality, speed, and the cost.
  • singingtoday 3 hours ago
    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.

  • paxys 4 hours ago
    Why not wait one more day for GPT-5.6?
    • foxfired 3 hours ago
      If we wait for the next models, we will never test anything because there will always be another model. Like the Ai Scotsman:

      > "Nay, laddie, that’s no’ the real AI Scotsman! He’s grander still! More powerful! Just wait for the next model!"

      • looksjjhg 1 hour ago
        I think he’s being sarcastic
    • faitswulff 3 hours ago
      Also throw in GLM 5.2 for good measure
    • m4rkuskk 4 hours ago
      That will be in the Part 2 article.
    • acters 3 hours ago
      I worry that GPT 5.6 will be heavily restricted and have the same feature to fallback to another model like Claude fable 5 does all too often. That fallback shenanigans mess up actual benchmarks and I don't like it.
    • fluidcruft 3 hours ago
      And why not Sonnet?
  • Kuyawa 3 hours ago
    I'd like to see the comparisons with DeepSeek, Qwen, Mimo, Kimi and GLM
  • Zebfross 3 hours ago
    Isn’t the number of turns most important? Some agents take repeated input, while others can mostly one-shot what I’m looking for.
  • brainless 51 minutes ago
    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.

  • kelvinjps10 2 hours ago
    Chat got ones were slow on Firefox mobile
  • Madmallard 41 minutes ago
    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.
  • thorum 3 hours ago
    Interesting that all four models converge on such similar designs, for such short prompts.
    • HeavyStorm 3 hours ago
      They were trained pretty much on the same data.
  • RickS 3 hours ago
    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.

  • RazorBucksICO 2 hours ago
    “The honest headline:”

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

    • Yiin 2 hours ago
      especially when using /humanizer is one prompt away
  • nrightnour 2 hours ago
    This is disgustingly biased. The conclusion is that Grok holds its own?! There was zero evidence of that.
  • yashthakker 1 hour ago
    [dead]
  • krauq 3 hours ago
    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.
  • maxdo 4 hours ago
    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 .

    • Tostino 2 hours ago
      Who the hell tries something that's been out a few hours and says "My work is not the same"?