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

GLM-5.2 is a step change for open agents

interconnects.ai

Post reply on HN
Print view View original

111–120 of 240 posts

Re: GLM-5.2 is a step change for open agents

#111

Post by linzhangrun »

mlmonkey wrote: post #61

Here are the numbers from their bar chart: 1. SWE-bench Pro Model Score (%) GLM-5.2 62.1 GLM-5.1 58.4 Claude Opus 4.8 69.2 GPT-5.5 58.6 Gemini 3.1 Pro 54.2 2. Terminal-Bench 2.1 Model Score (%) GLM-5.2 81.0 GLM-5.1 63.5 Claude Opus 4.8 85.0 GPT-5.5 84.0 Gemini 3.1 Pro 74.0 3. NL2Repo Model Score (%) GLM-5.2 48.9 GLM-5.1 42.7 Claude Opus 4.8 69.7 GPT-5.5 50.7 Gemini 3.1 Pro 33.4 4. DeepSWE Model Score (%) GLM-5.2 46.2…

Just waiting for the 3.5 Pro they said would come out this month. Gemini is pretty much useless for any serious work right now.

Re: GLM-5.2 is a step change for open agents

#112

Post by ipaddr »

ImaCake wrote: post #39
jerojero wrote: post #3

Open weight models from Chinese labs tend to be significantly cheaper. I think theyre absolutely needed. I can't afford 200 USD a month for personal use of coding AI, and I don't think such prices are reasonable for most of the world economy anyway. Not to mention US firms might be giving their employees a lot more than that. It's increasingly feeling, to me, that theres a gap building up between haves and have nots.…

Significantly cheaper than comparable models if you are using openrouter [0]. Just yesterday I spent roughly 13 cents centering some divs using Deepseek in a personal project. It would have been north of $1 to do that with a US frontier model. 0. https://openrouter.ai/compare/z-ai/glm-5.2/anthropic/claude-...

For centering divs the free models opencode offers can easily handle that work. DeepSeek V4 Flash is pretty decent.

Re: GLM-5.2 is a step change for open agents

#113

Post by esperent »

kreelman wrote: post #80
fbrncci wrote: post #69

Earlier quoted context omitted.

My costs are 0$ as any token or subscription spend on agents is invoiced as an expense to my clients.

Thanks so much for being bold enough to be fairly open about the costs, how you arrange billing and the advantages that's given you. I've been fooling around with DeepSeek 4 agentically. It's probably not as good as Anthropic offerings, but even those seem to be roiled in politics and strife and DeepSeek 4 is very good IMHO. I'll later try out GLM. I'm in Australia. The government has set up a "return and earn" schem…

> I'm using the Chinese DeepSeek provider, so everything done there could potentially be taken and used by the CCP

As opposed to Anthropic or OpenAI where everything done could potentially be taken and used by the US government.

Also, replace "could potentially" with "will definitely" in both cases, there's no conspiracy here.

We're stuck between two bad positions, so just use the one that's best for you, and wait for a better solution to arrive.

Re: GLM-5.2 is a step change for open agents

#114

Post by spwa4 »

try-working wrote: post #84
guybedo wrote: post #50

GLM-5.2 has been a step change in how fast i can burn through tokens. I subscribed to their max plan to try it out. It counted me 700M tokens and drained my weekly quota in under 2 days. Quota just reset less than 24h ago and i'm already >60% weekly quota usage. For reference the kind of work i did would have used somewhere between 3% and 5% of Codex max or Claude max. The model is good, the plan is a scam

Kimi and GLM models have coined a new term: Thinkslop. They run a chain of thought that is up to 10x longer than other models and it seems that through a lookback mechanism they are able to use the CoT to reason about solutions to tasks they couldn't otherwise solve. The downside is of course that they consume many more tokens off your plan, and also that they are significantly slower. Kimi K2.7 takes about 7x longer…

Turning up the thinking (max time spent thinking) lever really changes model performance, even for tiny models. But it's really irritating because it adds a lot of time.

Re: GLM-5.2 is a step change for open agents

#116

Post by lionkor »

arikrahman wrote: post #40
jerojero wrote: post #3

Open weight models from Chinese labs tend to be significantly cheaper. I think theyre absolutely needed. I can't afford 200 USD a month for personal use of coding AI, and I don't think such prices are reasonable for most of the world economy anyway. Not to mention US firms might be giving their employees a lot more than that. It's increasingly feeling, to me, that theres a gap building up between haves and have nots.…

Someone else on this forum put it well, U.S. is trying to achieve AGI at all costs, while Chinese models are seeking widespread adoption.

None of the AI companies in the US are on the path to AGI. They are, however, on the path to claiming they have AGI, then subsequently not releasing it and only giving it to the US government to make drones that can bomb the homes of political dissidents.

Re: GLM-5.2 is a step change for open agents

#117

Post by lionkor »

praveer13 wrote: post #10
tacomagick wrote: post #6

Earlier quoted context omitted.

DeepSeek through their own API has saved me tons of tokens honestly. Even though it is not as smart as Kimi or Claude, their level of entry is very low with a top up of 2$ and Pay as you go compared to the subscription of Claude or 20$ top up of Kimi

For personal use I’m considering using the frontier models from openai or anthropic to create a plan with research and brainstorming etc with enough details for cheap models to be able to follow (glm, deepseek etc) - with openrouter - will monitor how cheap and effective that turns out to be.

Seconding the recommendation to use Deepseek directly via the API. I've burnt 287 million tokens in the last couple of days, costing me a whopping $5.77 USD.

Re: GLM-5.2 is a step change for open agents

#119

Post by alpineman »

jerojero wrote: post #3

Open weight models from Chinese labs tend to be significantly cheaper. I think theyre absolutely needed. I can't afford 200 USD a month for personal use of coding AI, and I don't think such prices are reasonable for most of the world economy anyway. Not to mention US firms might be giving their employees a lot more than that. It's increasingly feeling, to me, that theres a gap building up between haves and have nots.…

With open weight models there is true inference competition. Whoever can serve the model at the lowest price. And the consumer wins. Capitalism, served by China.
Post reply on HN