Posted by meetpateltech 6 hours ago
> GLM-5 can turn text or source materials directly into .docx, .pdf, and .xlsx files—PRDs, lesson plans, exams, spreadsheets, financial reports, run sheets, menus, and more.
A new type of model has joined the series, GLM-5-Coder.
GLM-5 was trained on Huawei Ascend, last time when DeepSeek tried to use this chip, it flopped and they resorted to Nvidia again. This time seems like a success.
Looks like they also released their own agentic IDE, https://zcode.z.ai
I don’t know if anyone else knows this but Z.ai also released new tools excluding the Chat! There’s Zread (https://zread.ai), OCR (seems new? https://ocr.z.ai), GLM-Image gen https://image.z.ai and Voice cloning https://audio.z.ai
If you go to chat.z.ai, there is a new toggle in the prompt field, you can now toggle between chat/agentic. It is only visible when you switch to GLM-5.
Very fascinating stuff!
Solid bird, not a great bicycle frame.
Context for the unaware: https://simonwillison.net/tags/pelican-riding-a-bicycle/
It's just an experiment on how different models interpret a vague prompt. "Generate an SVG of a pelican riding a bicycle" is loaded with ambiguity. It's practically designed to generate 'interesting' results because the prompt is not specific.
It also happens to be an example of the least practical way to engage with an LLM. It's no more capable of reading your mind than anyone or anything else.
I argue that, in the service of AI, there is a lot of flexibility being created around the scientific method.
For the last generation of models, and for today's flash/mini models, I think there is still a not-unreasonable binary question ("is this a pelican on a bicycle?") that you can answer by just looking at the result: https://simonwillison.net/2024/Oct/25/pelicans-on-a-bicycle/
I'm guessing both humans and LLMs would tend to get the "vibe" from the pelican task, that they're essentially being asked to create something like a child's crayon drawing. And that "vibe" then brings with it associations with all the types of things children might normally include in a drawing.
Do electric pelicans dream of touching electric grass?
We need a new, authentic scenario.
I don't think there's a good description anywhere. https://youtube.com/@t3dotgg talks about it from time to time.
1. Take the top ten searches on Google Trends
(on day of new model release)
2. Concatenate
3. SHA-1 hash them
4. Use this as a seed to perform random noun-verb
lookup in an agreed upon large sized dictionary.
5. Construct a sentence using an agreed upon stable
algorithm that generates reasonably coherent prompts
from an immensely deep probability space.
You can generate a few such sentences for more samples.
Alternatively, take the top ten F500 stock performers. Some easy signal that provides enough randomness but is easy to agree upon and doesn't provide enough time to game.
It's also something teams can pre-generate candidate problems for to attempt improvement across the board. But they won't have the exact questions on test day.
This pattern of considering 90% accuracy (like the level we've seemingly we've stalled out on for the MMLU and AIME) to be 'solved' is really concerning for me.
AGI has to be 100% right 100% of the time to be AGI and we aren't being tough enough on these systems in our evaluations. We're moving on to new and impressive tasks toward some imagined AGI goal without even trying to find out if we can make true Artificial Niche Intelligence.
As far as I can tell for AIME, pretty much every frontier model gets 100% https://llm-stats.com/benchmarks/aime-2025
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.
I notice the people who endlessly praise closed-source models never actually USE open weight models, or assume their drop-in prompting methods and workflow will just work for other model families. Especially true for SWEs who used Claude Code first and now think every other model is horrible because they're ONLY used to prompting Claude. It's quite scary to see how people develop this level of worship for a proprietary product that is openly distrusting of users. I am not saying this is true or not of the parent poster, but something I notice in general.
As someone who uses GLM-4.7 a good bit, it's easily at Sonnet 4.5 tier - have not tried GLM-5 but it would be surprising if it wasn't at Opus 4.5 level given the massive parameter increase.
open weight models are not there at all yet.
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
Let's have a serious discussion. Just because Claude PR department coined the term benchmaxxing, we we should not be using it unless they shell out some serious monetes.
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.
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.
Here is the response from Gpt-5.2 using my default custom instructions in the mac desktop app.
OBJECTIVE: Decide whether to drive or walk to a car wash ~50 meters from home, given typical constraints (car must be present for wash).
APPROACH: Use common car-wash workflows + short-distance driving considerations (warm engine, time, parking/queue). No web sources needed (stable, local decision).
OUTPUT: • Default choice: Drive. A car wash generally requires the car on-site, and 50 meters of driving is trivial. • When walking makes sense: • You’re going to drop the car off (hand-wash/detail) and pick it up later. • You want to avoid moving the car now (ice, tight parking, you’ve been drinking, etc.) and someone else will handle the car. • Micro-guidance: • If it’s an automatic wash you stay in, drive. • If it’s detail/hand wash with a wait, drive there, then walk home (or just wait).
CONFIDENCE: 92/100 Assumptions: It’s a normal car wash that requires your car to be there; conditions are safe to drive 50 meters.
Which is exactly how you're supposed to prompt an LLM, is the fact that giving a vague prompt gives poor results really suprising?
The whole idea of this question is to show that pretty often implicit assumptions are not discovered by the LLM.
Since the goal is to get your car washed, the car needs to be at the car wash. If you walk, you will arrive at the car wash, but your car will still be sitting at home"
Are you sure that question is from this year?
"" [...] Since you need to get your car washed, you have to bring the car to the car wash—walking there without the vehicle won't accomplish your goal [...] If it's a self-service wash, you could theoretically push the car 50 meters if it's safe and flat (unusual, but possible) [..] Consider whether you really need that specific car wash, or if a mobile detailing service might come to you [...] """
Which seems slightly (unintentionally) funny.
But to be fair all the Gemini (including flash) and GPT models I tried did understand the quesiton.
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.
I noticed whenever such meme comes out, if you check immediately you can reproduce it yourself, but after a free hours it's already updated.
You should definitely drive.
If you walk there, your car will still be dirty back at your house! Since the goal is to get the car washed, you have to take it with you.
PS fantastic question!
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?
Maybe, but "intelligence" doesn't have a clear, agreed definition. And calling them "just token generators" skips over how complex that generation actually is.
"You’ll want to drive — you need the car at the car wash for them to wash it!
Even though it’s just 50 meters, the car has to be there. Enjoy the fresh clean car on the short drive back! "
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 above output is from GLM-5)
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.
You can have self-hosted models. You can have models that improve based on your needs. You can't have both.
OpenCode in particular has huge community support around it- possibly more than Claude Code.
Particularly for tool use.
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.
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?
When left to its own devices, GLM-4.7 frequently tries to build the world. It's also less capable at figuring out stumbling blocks on its own without spiralling.
For small, well-defined tasks, it's broadly comparable to Sonnet.
Given how incredibly cheap it is, it's useful even as a secondary model.
Certainly seems to remember things better and is more stable on long running tasks.
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...
And we will have Deepseek 4 in a few days...
Obviously for the average US tax payer getting along with China is in our interests - not so much our economic elites.
I use both Chinese and US models, and Mistral in Proton’s private chat. I think it makes sense for us to be flexible and not get locked in.
US bluff got called. A year back it looked like US held all the cards and could squeeze others without negative consequences. i.e. have cake and eat it too
Since then: China has not backed down, Europe is talking de-dollarization, BRICS is starting to find a new gear on separate financial system, merciless mocking across the board, zero progress on ukraine, fed wobbled, focus on gold as alternate to US fiat, nato wobbled, endless scandals, reputation for TACO, weak employment, tariff chaos, calls for withdrawal of gold from US's safekeeping, chatter about dumping US bonds, multiple major countries being quite explicit about telling trump to get fucked
Not at all surprised there is a more modest tone...none of this is going the "without negative consequences" way
>Mistral in Proton’s private chat
TIL
And yes, the consequence is strengthening the actual enemies of the USA, their AI progress is just one symptom of this disastrous US administration and the incompetence of Donald Trump. He really is the worst President of the USA ever, even if you were to just judge him on his leadership regarding technology... and I'm saying this while he is giving a speech about his "clean beautiful coal" right now in the White House.
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 i.e. those Blackwells etc...
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