[eli]

Neat. The frontier models have gotten pretty impressive, but they're all a bit too slow for interactive, human-in-the-loop coding. It incentivizes vibecoding and running multiple agents in parallel. A fast agent feels more like a partner.

For a while I was running Cerebras GLM 4.7 for a bunch of tasks. Not a very smart model, but it's fantastic to be have a live prototype of a site up and be able to type "make the fonts bigger. No not that big" and see it change in real time. And MiMo 2.5 is a lot more capable than GLM 4.7.

[ignoramous]

> And MiMo 2.5 is a lot more capable than GLM 4.7

MiMo 2.5 is not the same model as MiMo 2.5 Pro.

GLM 5.1 is z.ai's lastest iteration & is one of the popular open weight coding models.

If you've had the chance, how does GLM 5.1 (which is now more expensive than MiMo 2.5 Pro after its recent 70% price drop) compare?

[eli]

GLM 5.1 is very good. Definitely a contender for best open weight coding model. Nothing like 4.7.

But quite a bit more expensive than MiMo 2.5 Pro. Like 5x to 10x more on my little tests, at least by the API rates.

[maxdo]

i tried glm 4.7 for agents that write code. simple scripts 200-1000 LOC. extremely bad . Had to abandon cerebras oferning, their smart models are only on enterprise plan.

[jona-f]

glm 4.7 is quite old by now. I don't even use 5.1 anymore, cause I found kimi k2.6, mimi 2.5 pro, deepseek v4 pro and qwen 3.7 all better than glm 5.1