GLM-5.3-Flash Intelligence, Performance and Price Analysis

(artificialanalysis.ai)

121 points | by theanonymousone 3 hours ago

8 comments

  • CGamesPlay 2 hours ago
    Several factual errors about the model here. The input modalities are listed as text only, but the headline feature is image support. The context length should be 1048576 (so should GLM-5.3's, also wrong on the charts).

    https://docs.z.ai/guides/vlm/glm-5.3-flash#model-api

  • yipinwong 1 hour ago
    The analysis is still not compelling for me to switch from gtp5.6-luna to GLM-5.3-flash given

    - costs per task $0.05 vs $0.09

    - speed 130 vs 88

    - where GLM has only 5 more intelligence point: at this point few point is meaningless for most of models

    https://artificialanalysis.ai/models/comparisons/glm-5-3-fla...

    Been using Luna exclusively since the price drop, and i've been very satified with all tasks from planning, writing code, and other agent tasks. (just change thinking level from low <-> ultra)

    ---

    btw, I did try out Ox Alpha, the coding feels good but still not way better for me to switch to it.

    • BeetleB 44 minutes ago
      Which has a better monthly plan? Right now Z.ai "Pro" plan (the middle one) is $56/mo if you prepay for a year.

      I signed up for their Lite plan when it was only $28 for the whole year (less than $3/mo). Definitely very happy with that purchase!

    • psadri 1 hour ago
      Luna is at a very compelling point on the price/performance curve.

      I have found that sometimes a smaller model with max reasoning is actually more expensive than using the next tier model with a lower reasoning effort. It’s certainly faster.

    • jauntywundrkind 17 minutes ago
      I don't understand what would possibly make someone prefer speed over output? You'd rather get wrong bad answers that don't work as well very fast?

      In general I really don't mind waiting 5, 10, 40 minutes. There's other things I can look at, other plans or assessments or outputs aplenty stacking up. Its baffling beyond words to me that anyone would take speed over good output. Surely the better output is going to save enormous time in the long run, have better outcomes. What is it that addicts people so much to speed, especially when the difference is between fast and very fast?

    • vineyardmike 53 minutes ago
      I’ve been super pro-Luna lately. I really hope that Gemini-Flash-Lite is positioned to compete with it. We all know that Anthropic has abandoned Haiku and it would never be that cheap.

      Probably shouldn’t say this here but I’ve been planning to up my $20/mo exploratory ChatGPT subscription to the $100/mo tier as soon as I hit my cap. Between the progress and quality of Luna and their continuous resets, it’s been a few months now that I’ve lived off the $20 tier, frankly waiting for the need to upgrade, credit card in hand.

      I’m always trying new models, like many of us here, but the price is just so good for a well balanced, American, hosted model.

    • TacticalCoder 1 hour ago
      > The analysis is still not compelling for me to switch from gtp5.6-luna to GLM-5.3-flash given ...

      So Luna is competitive because a few weeks ago they did a 80% price drop?

      Many here said that 80% drop was not a move against Anthropic but a move against chinese models and your comments indicate that's the case.

  • m_ke 3 hours ago
    So how exactly is Anthropic and OpenAI ever going to pay back the trillions that they plan on spending?
    • Marha01 2 hours ago
      > So how exactly is Anthropic and OpenAI ever going to pay back the trillions that they plan on spending?

      It's really simple: if they truly get to human-level AI (or even superhuman AI), then money and debts no longer matter, since our current economic system will be obsolete. They are betting everything on this outcome.

      I don't know if they will manage to do it before their debts have to be repaid, but considering the rate of acceleration in the past few months, there is a non-trivial chance that they will, IMHO. We will see.

      • LeBit 1 hour ago
        That’s like building F1 cars and thinking you will soon have a rocket to land on the moon.

        LLM has nothing to do with AGI.

        • Marha01 57 minutes ago
          I would perhaps agree with you just a year ago. But now I am not so sure. It is clear that scaling up Transformers still leads to significant improvements, and they are now solving math conjectures and finding real vulnerabilites in software. We don't really know where the capability ceiling of the current approach is, and anyone telling you that we know it is lying to you.
          • shooly 21 minutes ago
            > We don't really know where the capability ceiling of the current approach is

            We do know, that the ceiling is below AGI. And it's not a matter of opinion - LLMs can not achieve AGI due to their design. Anyone telling you otherwise is lying to you.

            And it doesn't matter how many or how severe bugs they can find, because it's not about what they produce, but how they produce it.

            • Marha01 11 minutes ago
              > We do know, that the ceiling is below AGI. And it's not a matter of opinion - LLMs can not achieve AGI due to their design.

              [citation definitely needed]

              > And it doesn't matter how many or how severe bugs they can find, because it's not about what they produce, but how they produce it.

              AGI is defined by the practical outcomes, not by the way the outcomes are achieved. You have no way to know that scaled-up Transformers predicting the next token will never result in human-level intelligence, since we currently have no idea where the ceiling of that approach is.

      • my002 1 hour ago
        That's assuming that human-level AI is a possibility with current approaches.
        • traverseda 1 hour ago
          No, it's assuming there's a non-trivial chance that they will.
        • thatwasunusual 1 hour ago
          I'd assume we want at least human-level intelligence, but better than human-level _decision making_. ;)
    • gruez 2 hours ago
      You could ask the same about how z.ai, moonshot ai, minimax, and alibaba are going to continue training and releasing models for free.
      • npn 1 hour ago
        1. they still have revenue though. it might not enough to cover all the r&d but it is surely enough to cover the hardware cost.

        2. people tend to ignore this, but the salary budget of a US frontier lab and chinese frontier lab is nowhere comparable, the first can easily outdone the later by 100x.

        3. us labs, like other US style startups, always throw ton of money to capture the market. I don't see the chinese company doing the same scheme at all.

        so, surely chinese AI providers also lost money making new models, but they are not spending nearly as much as US ones.

        • gruez 1 hour ago
          >1. they still have revenue though. it might not enough to cover all the r&d but it is surely enough to cover the hardware cost.

          >2. people tend to ignore this, but the salary budget of a US frontier lab and chinese frontier lab is nowhere comparable, the first can easily outdone the later by 100x.

          Both arguments make it seem like there's a double standard for american vs chinese AI companies, where american labs are held up to strict standards for profitability, but chinese labs get a pass because [insert handwaving about how some aspect of chinese labs is different]. Let's do apples to apples comparisons here, what are both sides' run rates and revenue growth prospects?

          >3. us labs, like other US style startups, always throw ton of money to capture the market. I don't see the chinese company doing the same scheme at all.

          Right, instead they're releasing their models for free so competitors can undercut them on inference. American labs' prospect of "there are open models 90% as good but cost less" might seem bad, but chinese labs' prospect of "there are companies offering the exact same models but aren't on the hook for r&d spend" seems even worse.

        • applicative 1 hour ago
          Literally nothing is known about how these companies are financed. The usual story is that Moonshot was chosen when 'Mythos' occasioned a huge state crisis. China is the ascended masters of insane amounts of capital poured into whatever the state takes into its head next.
      • maxglute 26 minutes ago
        By charging $$$ like they do now and having a non terminal business model.

        PRC AI have lower opex and capex, i.e. export controls means they couldn't be trillions in the hole on inflated hardware in the first place. They only need to extract a few 10s of billions from domestic market have a healthy runway. If investors/gov wants to throw in a few billion to treat as utility, whatever, it's still rounding error.

        • jauntywundrkind 14 minutes ago
          Dirt cheap Chinese solar is a competitive advantage just sitting there waiting, but instead the US is trying to revive coal, restart a grossly ineffective small scale nuclear system with immensely bad fuel utilization, and spending billions to cancel renewable projects that were already approved. I'm so tired of these insurrectionist dog traitors to this country I love.
      • m_ke 2 hours ago
        just like there were mistrals, coheres, llamas, etc, there will be new deepseeks and moonshots if those ever flame out (worst case, given out at cost by google, meta, alibaba or etc)

        OpenAI and Anthropic are already in a ~200bil hole from previous model iterations and are committing to trillions of additional spending

        OpenAI spent more TBPN than kimi spent on training K3

      • maxglute 27 minutes ago
        By charging $$$ like they do now and having a non retarded business model. PRC AI have lower opex and capex, i.e. export controls means they couldn't be trillions in the hole on inflated hardware in the first place. They only need to extract a few 10s of billions from domestic market have a healthy runway. If investors/gov wants to throw in a few billion to treat as utility, whatever, it's still rounding error.
      • WarmWash 2 hours ago
        They are owned by the state, so the economics are a bit different.
        • gruez 1 hour ago
          >They are owned by the state

          They are by all accounts, not. Z.ai for instance is a public company according to wikipedia. Moonshot AI is private but all their investors are private companies. Alibaba, as we all know, is a massive publicly traded tech conglomerate.

          Moreover even if we take the more charitable view that they're controlled by the CCP, and therefore will continue releasing models for free, that seems as questionable as the prospect that private investors will continue shoveling money into anthropic/openai.

          • WarmWash 1 hour ago
            China has "classroom game capitalism", where companies can play the game, but the teacher still has uncontested, absolute, unilateral control in everything and anything. All the parameters of the game are managed by the teacher, and the teacher is the one who creates the foundations for the direction they want the game to move in.

            Don't forget, Jack Ma of "publicly owned" Alibaba, had to go into classroom time out after seemingly forgetting that its classroom capitalism and not real world capitalism.

          • applicative 43 minutes ago
            The core employees of z.ai are billionaires, because of the equity given to them in the past, which in their system is not antecedently evaluated. Much of the past annual expenditure of OpenAI has been the same, handing out equity - but because of the different legal system it is given an evaluation and listed as expenditure. Meanwhile the expenditure on compute for training and inference are apples and oranges again as the state is all over this with moonshot and z.ai and so on .
      • epolanski 2 hours ago
        At a fraction of the cost.
        • gruez 1 hour ago
          Shoveling 70% less money into a money pit is still shoveling money into a money pit. Not to mention that at least openai/anthropic has better prospects of making back the money because their models are proprietary, and won't be cannibalized by other companies serving the exact same models.
    • Haven880 2 hours ago
      Socialize the lost.They dont have to. You pay.
    • yogthos 2 hours ago
      I expect they're going to fight each other to become the vendor of record for the government, and whoever wins will get bailed out. This is one area where they don't have to worry about competition from Chinese models.
    • applicative 1 hour ago
      Its more Google Amazon Meta Microsoft who are spending trillions. They will be fine. So will Anthropic and OpenAI. Nvidia will presumably survive. The losses are all the real estate interests and contractors and contributory hardware companies etc.
    • vrganj 3 hours ago
      Why do you think tech oligarchs have been cozying up to the Trump admin? They're angling for a government bailout, paid for by your tax money!
      • ptdcc 2 hours ago
        Thy cozy up to whoever is in government. They cozy'd up with Biden too.
        • vrganj 2 hours ago
          That's true. But it's been a while since an admin was as brazenly corrupt and the cozying up was so promising.
        • Forgeties79 2 hours ago
          I think most of us can see that the level of corruption we are seeing with the administration is quite historical. You can’t simply say “both administrations engaged in corruption” and consider the matter closed. Scale matters.
  • AnodicElegy 3 hours ago
    Impressive. It kicked everything between itself and Sol xhigh out of the Pareto frontier. Can't wait to try it out.
  • jhack 2 hours ago
    Better than the latest Deepseek v4 Pro while being 3x cheaper in cost per task. Impressive!
  • a012 2 hours ago
    Can’t wait to try this out, and the only missing from this model for me is Image input support
    • minimaxir 2 hours ago
      It has image/video input support (that is surprisingly good)
  • croemer 1 hour ago
    Why does the top card say "Intelligence #1/173" when the bar chart further down shows it only at position 7?

    And the model isn't even shown in the speed bar chart just below. Such slop (the artificial intelligence website linked)

    • kzrdude 1 hour ago
      Not clear to me how it selects that, but it considers it to be #1 out of 173 models "of the same class".
      • croemer 1 hour ago
        I see, thanks, then it should state that in the card.
  • hn7jmxa7oc 2 hours ago
    [dead]