I am still waiting if they'd launch GLM-5 Air series,which would run on consumer hardware.
Full list of models provided : https://dev.synthetic.new/docs/api/models
Referal link if you're interested in trying it for free, and discount for the first month : https://synthetic.new/?referral=kwjqga9QYoUgpZV
Why is GLM 5 more expensive than GLM 4.7 even when using sparse attention?
There is also a GLM 5-code model.
2. cost is only a singular input into price determination and we really have absolutely zero idea what the margins on inference even are so assuming the current pricing is actually connected to costs is suspect.
Although it doesn't really matter much. All of the open weights models lately come with impressive benchmarks but then don't perform as well as expected in actual use. There's clearly some benchmaxxing going on.
Particularly for tool use.
Agreed. I think the problem is that while they can innovate at algorithms and training efficiency, the human part of RLHF just doesn't scale and they can't afford the massive amount of custom data created and purchased by the frontier labs.
IIRC it was the application of RLHF which solved a lot of the broken syntax generated by LLMs like unbalanced braces and I still see lots of these little problems in every open source model I try. I don't think I've seen broken syntax from the frontier models in over a year from Codex or Claude.
That being said, this model is MIT licensed, so it's a net benefit regardless of being benchmaxxed or not.
something that is at parity with Opus 4.5 can ship everything you did in the last 8 weeks, ya know... when 4.5 came out
just remember to put all of this in perspective, most of the engineers and people here haven't even noticed any of this stuff and if they have are too stubborn or policy constrained to use it - and the open source nature of the GLM series helps the policy constrained organizations since they can theoretically run it internally or on prem.
You're assuming the conclusion
The previous GLM-4.7 was also supposed to be better than Sonnet and even match or beat Opus 4.5 in some benchmarks ( https://www.cerebras.ai/blog/glm-4-7 ) but in real world use it didn't perform at that level.
You can't read the benchmarks alone any more.
If it's anywhere close to those models, I couldn't possibly be happier. Going from GLM-4.7 to something comparable to 4.5 or 5.2 would be an absolutely crazy improvement.
Before you get too excited, GLM-4.7 outperformed Opus 4.5 on some benchmarks too - https://www.cerebras.ai/blog/glm-4-7 See the LiveCodeBench comparison
The benchmarks of the open weights models are always more impressive than the performance. Everyone is competing for attention and market share so the incentives to benchmaxx are out of control.
I'm not immediately discounting Z.ai's claims because they showed with GLM-4.7 that they can do quite a lot with very little. And Kimi K2.5 is genuinely a great model, so it's possible for Chinese open-weight models to compete with proprietary high-end American models.
Those of us who just want to get work done don't care about comparisons to old models, we just want to know what's good right now. Issuing a press release comparing to old models when they had enough time to re-run the benchmarks and update the imagery is a calculated move where they hope readers won't notice.
There's another type of discussion where some just want to talk about how impressive it is that a model came close to some other model. I think that's interesting, too, but less so when the models are so big that I can't run them locally anyway. It's useful for making purchasing decisions for someone trying to keep token costs as low as possible, but for actual coding work I've never found it useful to use anything other than the best available hosted models at the time.
That you think corporations are anything close to quick enough to update their communications on public releases like this only shows that you've never worked in corporate
OpenCode in particular has huge community support around it- possibly more than Claude Code.
Today's meme was this question: "The car wash is only 50 meters from my house. I want to get my car washed, should I drive there or walk?"
Here is Claude's answer just right now:
"Walk! At only 50 meters (about 150 feet), it would take you less than a minute to walk there. Driving such a short distance would actually be less convenient - by the time you get in the car, start it, drive, and park, you could already be there on foot. Plus, you'd save fuel and your car would be right there waiting for you after the wash is done."
Here is ChatGPT, also right now:
"Since it’s only *50 meters* (about 160 feet), walking makes a lot more sense.
Here’s why:
* *It’s extremely close* — you’ll get there in under a minute. * *Driving would actually be less efficient* — by the time you start the car, move it, and park, you’re already there. * *Cold starts aren’t great for your engine* — very short drives don’t let the engine warm up properly. * *It saves fuel and emissions*, even if it’s a tiny amount. * You avoid the hassle of maneuvering such a short distance.
The only time driving might make sense is if:
* The weather is terrible (heavy rain, snow, extreme cold). * You have mobility issues. * The car wash requires you to stay in the vehicle and you don’t want to leave it there.
Otherwise, this is a perfect “walk it over” situation. "
Please save us all that talk about frontier and SOTA and that only the closedAI models are any good and the others are all so bad and benchmaxxed. For most purposes a Toyota is just as good as a BMW or a Merc or whatever luxury brand tickles your fancy. Even worse, the lastest 80B Qwen Next is not far from Opus 4.6 but runs on my laptop.
This is a classic logistical puzzle!
Unless you have a very unique way of carrying your vehicle, you should definitely drive.
If you walk there, you'll arrive at the car wash, but your car will still be dirty back at your house. You need to take the car with you to get it washed.
Would you like me to check the weather forecast for $mytown to see if it's a good day for a car wash?
This is a silly test for the big coding models.
This is like saying "all calculators are the same, nobody needs a TI-89!" and then adding 1+2 on a pocket calculator to prove your point.
Since you presumably want the car to be clean, the answer depends entirely on how the car is getting washed. The Breakdown If it’s a Professional Car Wash: You’ll need to drive. Bringing the car to the wash is generally the prerequisite for them washing it. Plus, walking 50 meters just to ask them to come pick up a car that is visible from their front door might result in some very confused looks from the staff. If it’s a Self-Service Pressure Washer: Again, drive. Dragging a 1,500kg vehicle 50 meters by hand is an incredible workout, but probably not the "quick chore" you had in mind. If you are hiring a Mobile Detailer: Walk. Stroll over there, tell them where you're parked, and walk back home to watch TV while they do the work in your driveway.
Distance: 50 meters (very short).
Goal: Get the car washed.
Decision: Drive or walk?
2. Evaluate the Options:
Option A: Walk
Pros: Healthy, environmentally friendly, no need to find parking (though it's close), easy to chat with neighbors.
Cons: The car is left at the car wash. The user can't "walk" the car to the car wash. The car must be moved to the car wash to be washed.
Option B: Drive
Pros: Moves the car to the location where the service is performed. It's the only logical way to get the car washed.
Cons: Driving 50 meters is technically bad for a cold engine (short trips), uses a negligible amount of fuel, might seem lazy.
3. Identify the Logical Flaw/Humor:
The user is asking if they should walk to get their car washed.
Unless the car wash involves someone coming to their house (mobile wash) or carrying the car, the car must be at the car wash.
Walking to the car wash leaves the car at home. Walking back from the car wash leaves the car at the car wash.
Therefore, the user must drive the car to the car wash.
4. Formulate the Answer:
Direct Answer: You should drive.
Reasoning: The car needs to be at the car wash to be washed. You cannot walk the car there.
Nuance/Context: 50 meters is a very short distance. Driving a car such a short distance is generally not great for the engine (doesn't allow oil to circulate/warm up properly), but it is necessary in this specific case.
Alternative (if applicable): Is there a mobile wash option? If so, walking isn't even needed. But assuming a standard car wash bay: Drive.
5. Drafting the response (Internal Monologue/Trial Phrases):
Draft 1: You have to drive. You can't wash the car if it's at your house and you are at the car wash.
Draft 2: You should drive. Since the car needs to be washed, it needs to be at the car wash. Walking there doesn't help get the car clean.
Refining for clarity and wit: Point out the obvious - the car is the object being washed. It needs to move.
Final Polish (similar to the provided good output):
State clearly: You should drive.
Explain why: The car needs to be there.
Add a practical note: Driving 50 meters is a bit silly for engine health, but unavoidable here.
Consider the scenario of "walking back": Maybe the user meant "walk back"? No, the prompt says "drive there or walk there". The intent is transportation to the location.
6. Constructing the final output:
"You should definitely drive."
"Why? Because the car wash cleans the car, so the car needs to be at the car wash. If you walk, the car stays at home."
"Additional thought: Driving 50 meters is technically a 'cold start' short trip which isn't ideal for the engine, but it's the only way to get the service done!"
Final Output Generation (matching the logic above).
You should drive.
Here is why:
1. The car needs to be there: You are getting the car washed, so the car must be at the car wash. You cannot walk the car there by yourself.
2. Efficiency: Driving 50 meters takes about 10 seconds. Walking 50 meters takes about a minute, but you would be leaving the car behind.
The only exception is if you are planning to get a mobile car wash (where they come to you) or if you are dropping the car off and walking back home while they clean it. But to simply "get there," you must drive.
(The output above is from GLM-5)
Maybe, but "intelligence" doesn't have a clear, agreed definition. And calling them "just token generators" skips over how complex that generation actually is.
But this here is excellent value, if they offer it as part of their subscription coding plan. Paying by token could really add up. I did about 20 minutes of work and it cost me $1.50USD, and it's more expensive than Kimi 2.5.
Still 1/10th the cost of Opus 4.5 or Opus 4.6 when paying by the token.
Care to elaborate more?
In my personal benchmark it's bad. So far the benchmark has been a really good indicator of instruction following and agentic behaviour in general.
To those who are curious, the benchmark is just the ability of model to follow a custom tool calling format. I ask it to using coding tasks using chat.md [1] + mcps. And so far it's just not able to follow it at all.
I'm developing a personal text editor with vim keybindings and paused work because I couldn't think of a good interface that felt right. This could be it.
I think I'll update my editor to do something like this but with intelligent "collapsing" of extra text to reduce visual noise.
Have you had good results with the other frontier models?
>China’s philosophy is different. They believe model capabilities do not matter as much as application. What matters is how you use AI.
>The main flaw is that this idea treats intelligence as purely abstract and not grounded in physical reality. To improve any system, you need resources. And even if a superintelligence uses these resources more effectively than humans to improve itself, it is still bound by the scaling of improvements I mentioned before — linear improvements need exponential resources. Diminishing returns can be avoided by switching to more independent problems – like adding one-off features to GPUs – but these quickly hit their own diminishing returns.
Literally everyone already knows the problems with scaling compute and data. This is not a deep insight. His assertion that we can't keep scaling GPUs is apparently not being taken seriously by _anyone_ else.
While I do understand your sentiment, it might be worth noting the author is the author of bitandbytes. Which is one of the first library with quantization methods built in and was(?) one of the most used inference engines. I’m pretty sure transformers from HF still uses this as the Python to CUDA framework
> They believe model capabilities do not matter as much as application.
Tell me their tone when their hardware can match up.
It doesn't matter because they can't make it matter (yet).
Edit: Input tokens are twice as expensive. That might be a deal breaker.
Solid bird, not a great bicycle frame.
Context for the unaware: https://simonwillison.net/tags/pelican-riding-a-bicycle/
US attempts to contain Chinese AI tech totally failed. Not only that, they cost Nvidia possibly trillions of dollars of exports over the next decade, as the Chinese govt called the American bluff and now actively disallow imports of Nvidia chips as a direct result of past sanctions [3]. At a time when Trump admin is trying to do whatever it can to reduce the US trade imbalance with China.
[1] https://tech.yahoo.com/ai/articles/chinas-ai-startup-zhipu-r...
[2] https://www.techradar.com/pro/chaos-at-deepseek-as-r2-launch...
[3] https://www.reuters.com/world/china/chinas-customs-agents-to...
Has any of these outfits ever publicly stated they used Nvidia chips? As in the non-officially obtained 1s. No.
> US attempts to contain Chinese AI tech totally failed. Not only that, they cost Nvidia possibly trillions of dollars of exports over the next decade, as the Chinese govt called the American bluff and now actively disallow imports of Nvidia chips
Sort of. It's all a front. On both sides. China still ALWAYS had access to Nvidia chips - whether that's the "smuggled" 1s or they run it in another country. It's not costing Nvidia much. The opening of China sales for Nvidia likewise isn't as much of a boon. It's already included.
> At a time when Trump admin is trying to do whatever it can to reduce the US trade imbalance with China
Again, it's a front. It's about news and headlines. Just like when China banned lobsters from a certain country, the only thing that happened was that they went to Hong Kong or elsewhere, got rebadged and still went in.
Uh yes? Deepseek explicitly said they used H800s [1]. Those were not banned btw, at the time. Then US banned them too. Then US was like 'uhh okay maybe you can have the H200', but then China said not interested.
Then they haven't. I said the non-officially obtained 1s that they can't / won't mention.
Last time there was a hype about GLM coding model, I tested it with some coding tasks and it wasn’t usable when comparing with Sonnet or GPT-5
I hope this one is different
Claude Opus 4.6: 65.5%
GLM-5: 62.6%
GPT-5.2: 60.3%
Gemini 3 Pro: 59.1%
We already know that intelligence scales with the log of tokens used for reasoning, but Anthropic seems to have much more powerful non-reasoning models than its competitors.
I read somewhere that they have a policy of not advancing capabilities too much, so could it be that they are sandbagging and releasing models with artificially capped reasoning to be at a similar level to their competitors?
How do you read this?
eugene3306•2h ago
Bolwin•1h ago
falcor84•1h ago
eugene3306•1h ago