Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GLM-5.2 is the new leading open weights model on Artificial Analysis

artificialanalysis.ai

Post reply on HN
Print view View original

321–330 of 476 posts

Re: GLM-5.2 is the new leading open weights model on Artificial Analysis

#321

Post by anuramat »

CuriouslyC wrote: post #175
anuramat wrote: post #32

Earlier quoted context omitted.

> unlimited tokens for $50 a month link? > Why imho everything but opus produces unusable code (fable was even better...), eg gpt5.5 seems to write the absolute worst code that still technically solves the problem; tbh I'd be totally willing to trade "raw intelligence" for "code taste" more labs need to figure out whatever anthropic did to destroy everybody else on frontiercode bench

Opus has the nickname "Slopus" in a lot of circles for a reason. It can write nice code in isolation, but the way it organizes that code and its rigor in addressing edge cases/making sure things are robust leave a lot to be desired. Opus is particularly famous for having a real problem reinventing stuff that already existed in the codebase because it wanted to get to work before exploring sufficiently.

what you're describing doesn't sound like such a big deal -- it's (A) obvious during review, (B) easy to fix in a single prompt, (C) simple enough to fix manually, (D) can be mitigated with tokenmaxxing (agent review passes, prompting, subagents, etc)

regarding edge cases -- less is more in my experience, as removing is harder than adding

Re: GLM-5.2 is the new leading open weights model on Artificial Analysis

#322

Post by sinuhe69 »

RDTvlokip wrote: post #238

I have a question, as it happens: Do you think the benchmarks and models were trained on benchmark datasets to skew the results, even though in real-world applications we realize they're not that great?

Recent incident with the Rio 3.5 model clearly shows that many coding models are specifically trained/fine tuned for the benchmarks.

Re: GLM-5.2 is the new leading open weights model on Artificial Analysis

#323

Post by guybedo »

It's probably a good model but they used GLM 5.1 to code their infra.

I signed up to their max plan yesterday, did some light coding work, and i'm at 180M tokens used and 40% weekly quota gone.

Even when tokenmaxxing on the Claude Max or GPT $200 plan, i couldn't get more than 20% quota gone per day.

Re: GLM-5.2 is the new leading open weights model on Artificial Analysis

#324

Post by sinuhe69 »

enraged_camel wrote: post #204
piterrro wrote: post #191

DeepSeek v4 pro is still 10x cheaper than GLM-5.2 and the quality is still enough for 95% of coding tasks.

People always say stuff like this, but it is misleading. The reason it's misleading is because that remaining 5% makes a huge difference, and is where most of the value of using AI agents lies. I'm not interested in using AI to write code that would have taken me 5-10 minutes to write myself. I use AI to debug complex bugs and develop large features that span multiple domains - stuff that normally takes hours, if not…

I get what you mean. But for many people, AI coding is not about solving complex problems. No, they do it mostly themselves. AI coding for many is a productivity tool, where it helps you with mundane, but laborious tasks.

In my setup, I use a daily workhorse for such things. They should be fast, cheap and reasonably working well. I don’t expect it to be smart, but need it to follow instructions perfectly and handle tool calling well.

For architectural work or debugging help, I use the top models instead.

That works reasonably well for me with a low cost.

Re: GLM-5.2 is the new leading open weights model on Artificial Analysis

#325

Post by computerex »

Schiendelman wrote: post #37
andai wrote: post #31

Earlier quoted context omitted.

But it just works with Claude Code? They have a guide on their website. https://docs.z.ai/devpack/tool/claude Here's my setup. I add this to my .bashrc export ZAI_API_KEY="your_key_here" alias claudez='ANTHROPIC_AUTH_TOKEN="$ZAI_API_KEY" ANTHROPIC_BASE_URL=" https://api.z.ai/api/anthropic " ANTHROPIC_DEFAULT_OPUS_MODEL="glm-5.2[1m]" ANTHROPIC_DEFAULT_SONNET_MODEL="glm-4.7" ANTHROPIC_DEFAULT_HAIKU_MODEL="glm-4.7" clau…

Sure, I'm not saying I, a software engineer, cannot do this. I'm saying it's significant onboarding friction . Unless this were a massive differentiator, people aren't going to be "talking about it" the way GP suggests!

Not really, you can literally have Claude set it up for you.

Re: GLM-5.2 is the new leading open weights model on Artificial Analysis

#326

Post by eckelhesten »

Alifatisk wrote: post #207
eckelhesten wrote: post #91

Sure, but whatever you do, don't buy their (Z.ai) lite plan. I feel like i threw 15 dollars in the sea. I'm getting rate limited after 3-4 prompts. You get way less value than just paying 25 dollars for Claude or OpenAI models.

Did you consider their peak hours and model usage multiplier? Read the green box https://docs.z.ai/devpack/overview#usage-instruction I had the Lite plan, I NEVER maxed out the quota because I considered these things. If I, for example, switched over to GLM-5-Turbo, then I could've easily burned through quota.

I just read it and honestly it left an even worse taste in my mouth.

>GLM-5.2 and GLM-5-Turbo are advanced models designed to rival Claude Opus model. Its usage will be deducted at 3 × during peak hours and 2 × during off-peak hours.

Claude certainly does not punish me for using their best models. Why should this "up and coming" company do it?

I thought the up and coming ai companies was supposed to have some kind of leverage in terms of price/performance (see deepseeks insanely cheap V4 flash and pro).

Re: GLM-5.2 is the new leading open weights model on Artificial Analysis

#327

Post by applicative »

JKCalhoun wrote: post #232
applicative wrote: post #206

Earlier quoted context omitted.

> China is going to eat the US lunch on AI They will forever have superior weights?

I would imagine it will be a fundamental breakthrough, not weights alone, that are going to usher in the next generation of AI. Perhaps China will in fact make that breakthrough. They certainly seem to have a lot of eyeballs in the field right now.

There has really been one break-through, the actual construction of giant LLMs from the available titanic corpus of text. Even that barely involved much conceptual breakthrough, a few things maybe e.g. transformer. Basically it was a question of the accessibility of a) giant internet corpus of actual people actually saying stuff and b) adequate computing power. The witty surface training, the scaffolding for a chatbot is what made a universal stir. With this, though, we are done with revolutionary breakthroughs. Training for coding involves actual alteration of weights - and as it improves the general utility of the corresponding models will fail. In the end it will be a domain of specialized models. The improvement of this aspect via RLVR etc is what caused a general mania in the programmer milieu.

There is a lot of money in pretending that we are seeing unending revolutions.

Re: GLM-5.2 is the new leading open weights model on Artificial Analysis

#328

Post by eckelhesten »

granra wrote: post #312
eckelhesten wrote: post #153

Earlier quoted context omitted.

Try pointing it to a small codebase, or even ask it to conjure information found online. You'll see that it quickly gives up. Thing is, they seem to count cached hits as if they were the non-cached tokens. I wont be subscribing again thats for sure. I am not paying iPhone money for a Xiaomi.

That's what I've been doing. I use crush normally. While the codebase are by no means huge, they're not tiny either.

Are you using it in an agentic workflow? Just reading the codebase will consume a lot of cached tokens, but seemingly, z.ai counts these as normal input tokens the way they're rate limiting.

Re: GLM-5.2 is the new leading open weights model on Artificial Analysis

#330

Post by granra »

eckelhesten wrote: post #326
Alifatisk wrote: post #207

Earlier quoted context omitted.

Did you consider their peak hours and model usage multiplier? Read the green box https://docs.z.ai/devpack/overview#usage-instruction I had the Lite plan, I NEVER maxed out the quota because I considered these things. If I, for example, switched over to GLM-5-Turbo, then I could've easily burned through quota.

I just read it and honestly it left an even worse taste in my mouth. >GLM-5.2 and GLM-5-Turbo are advanced models designed to rival Claude Opus model. Its usage will be deducted at 3 × during peak hours and 2 × during off-peak hours. Claude certainly does not punish me for using their best models. Why should this "up and coming" company do it? I thought the up and coming ai companies was supposed to have some kind of…

With a claude code plan, can you generate as many tokens with Opus as you can with Haiku before filling your 5 hour window? The same is going on here.
Post reply on HN