GLM-5.2 is the new leading open weights model on Artificial Analysis • Hacker News Board

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

#421

Post by enraged_camel » Thu, Jun 18, 2026, 3:10 AM UTC

sinatra wrote: post #410

unrvl22 wrote: post #4

Why aren't more people talking about this? It's literally Opus 4.7 quality stupid prices. I know providers who are offering this at unlimited tokens for $50 a month. Some are even offering API rates at 3x lower than the official ZAI api rates which are already like 10x cheaper than Opus. (Crof and Umans btw) This is a huge blow to Anthropic/OpenAI/Google and a massive win for the rest of the world. The official API p…

I've tried Chinese open models few times before. They were fine, but they didn't come close to the benchmarks they were claiming. Now, maybe GLM 5.2 is close to Opus 4.7, but I don't wanna keep checking them and keep finding that they're still benchmaxing and aren't at GPT (my choice) or Opus level. The boy who cried wolf, I guess.

Yes, my experience has been the same as yours. I find that the performance of open models is quite acceptable, even good, at one-off questions or small tasks. But they are quite unreliable at long horizon goals.

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

#422

Post by tomerbd » Thu, Jun 18, 2026, 3:41 AM UTC

I code daily with AI - real programming tasks, professional, real work, read customers, I use below 3:

- codex 5.5 medium - best results less hand holding medium speed

- opus 4.8 max - mediocre with hand holding medium speed

- glm 5.2 max - mediocre with hand holding and super slow

- composer 2.5 - mediocre with hand holding and super fast

I use all, since i run mulitple coding in parallel. disclosure - I use rexide which we created for all these agents to run in parallel with good visibility and feedback.

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

#423

Post by aunty_helen » Thu, Jun 18, 2026, 4:24 AM UTC

Before you go and sign up to the max plan like I did, they are obviously struggling for capacity. I'm getting API rate limited and 429'd on a simple "hello"

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

#424

Post by brookst » Thu, Jun 18, 2026, 4:28 AM UTC

mannanj wrote: post #202

vitalyan123 wrote: post #80

Earlier quoted context omitted.

distillation of thinking models is not particularly effective - both "Open"AI and Misanthropic don't show you the real chain of thought, only its severely downscaled version. both do everything in their power to combat such outrageous copyright infringement, so the bulk of unethically scrapped data the Chinese have is from several generations ago.

The companies that did copyright infringement and unethically scrapped data think that copyright infringement and unethically scrapping data is wrong and needs to be stopped. Though only in particular situations, like when it’s done to them and not when they do it. Cause they have the power and are morally right and know better than you. And if you question this at all, well you’re a threat to American values and a s…

It’s been amazing to see the arc of tech people going from “evil Disney, copyright is an abomination, information wants to be free” to “OMG copyright is inviolable and AI is taking money out of Plato’s descendants’ pockets!”

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

#425

Post by majormajor » Thu, Jun 18, 2026, 4:35 AM UTC

chartpath wrote: post #383

matheusmoreira wrote: post #359

Earlier quoted context omitted.

> GLM 5.2 Max = Opus 4.8 Max in thinking behavior This is insane! I can't wait until technology progresses to the point we can run these things on consumer hardware!

Are there any indications that this will be possible? Consumer hardware will continue getting better but I can't see 512GB RAM in a MacBook Pro any time soon. I'm hoping linear attention techniques plus MoE will make breakthroughs in size/compression and throughput.

In the last ten years laptop memory footprints have, what, doubled at the low end? Smallest MacBook Pro in 2016 was 8GB, smallest is 16GB today? Max I think has gone up 8x meanwhile, 16 to 128?

I wonder if there's a bit of a chicken-and-egg issue where there wasn't much that demanded 10x the RAM, so there wasn't much pressure to develop more or increase production to support it at consumer prices.

There's wayyyyyyy more demand for memory generally now, so assuming it's not a demand bubble that pops rapidly, I'd expect the new normal to end up at a much higher baseline. 512GB would be 4x greater than today's max, so even with the relatively slow last 10 years development pace, give it five years max?

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

#426

Post by gertlabs » Thu, Jun 18, 2026, 4:43 AM UTC

nsoonhui wrote: post #413

gertlabs wrote: post #316

GLM 5.2 is the first model we've tested that is unambiguously on par with, or better than Opus 4.6 (although as usual, we have GLM 5.2 and most other Chinese models a bit below most other benchmarks with more vulnerable test methodologies). Data at https://gertlabs.com/rankings

I really have to take your score with a grain of salt because Opus 4.5 does better than Opus 4.6

They're within confidence intervals of each other, but remember how much discussion there was that Opus 4.6 had been nerfed in March. We averaged samples over the entire lifetime of Opus 4.6, which likely served many different underlying checkpoints. Even the best version of Opus 4.6 was hardly an upgrade.

We find a lot of interesting anomalies with our benchmark that hold up under large sample sizes.

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

#427

Post by sankalpmukim » Thu, Jun 18, 2026, 4:49 AM UTC

sterlind wrote: post #404

muyuu wrote: post #399

Earlier quoted context omitted.

you need 8 x 96GB Blackwell or equivalent so around US$150k which is Small/Medium-Enterprise territory already, but who knows when it will hit "reasonable" home consumer territory I think there's hope future generations of unified memory machines may get this sort of memory availability when new fabs open in then next couple of years and then ramp up production for a few years afterwards - that makes ~2030s credible…

there are cheaper ways to do it. not like, consumer-cheap, but I'm setting up a rig for 80% cheaper than that. I'm a tad worried about triggering a run on the particular hardware I'm buying though so I'll leave it vague here, but hit me up on Discord if you're curious.

Hey, very intrigued about how it can be done for cheaper. Sent a friend request to sterlind on Discord, interested if you do a write up

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

#428

Post by HWR_14 » Thu, Jun 18, 2026, 4:49 AM UTC

Tiberium wrote: post #2

It seems to really be a nice step-up and is getting quite close to the frontier. I wish they'd start focusing on the reasoning efficiency now, though. I have a simple (relatively) test task to evaluate LLMs: writing a simple math evaluator library in Nim (it's about 400-600 lines total max), and GLM 5.2 (xhigh which maps to max effort) spent over 15 minutes (!) reasoning, spending about 45k tokens, before it finally…

I thought you could not compare tokens across models because their cost and speed was so different between models.

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

#429

Post by celrod » Thu, Jun 18, 2026, 4:57 AM UTC

matheusmoreira wrote: post #363

papersail wrote: post #273

Earlier quoted context omitted.

rank score age size name 1 62.0 8 - Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) 2 59.1 55 - GPT-5.5 (xhigh) 3 58.5 55 - GPT-5.5 (high) 4 57.2 104 - GPT-5.4 (xhigh) 5 56.7 20 - Claude Opus 4.8 (Adaptive Reasoning, Max Effort) 6 55.5 118 - Gemini 3.1 Pro Preview 7 53.1 62 - Claude Opus 4.7 (Non-reasoning, High Effort) 8 53.1 132 - GPT-5.3 Codex (xhigh) 9 52.5 62 - Claude Opus 4.7 (Adaptive Reason…

These results are amazing! I can't believe an open weight model rivals Opus 4.6, my most used model!

That list also places Sonnet 4.6 above Opus 4.6, which doesn't match my experience.

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

#430

Post by solid_fuel » Thu, Jun 18, 2026, 5:05 AM UTC

brookst wrote: post #424

mannanj wrote: post #202

Earlier quoted context omitted.

The companies that did copyright infringement and unethically scrapped data think that copyright infringement and unethically scrapping data is wrong and needs to be stopped. Though only in particular situations, like when it’s done to them and not when they do it. Cause they have the power and are morally right and know better than you. And if you question this at all, well you’re a threat to American values and a s…

It’s been amazing to see the arc of tech people going from “evil Disney, copyright is an abomination, information wants to be free” to “OMG copyright is inviolable and AI is taking money out of Plato’s descendants’ pockets!”

> taking money out of Plato’s descendants’ pockets

Yeah, remind me - is it Plato's descendants that people are concerned about here, or is it every single author who had any work in Anna's Archive, any work published online, any work published on github, etc?

I think that people are probably upset about the harm to living people who had their work stolen by Meta and other LLM companies - regardless of license, terms of use, or any other attempted protection.