Not true since a few months, genuinely try GLM 5.2 and Minimax M3, especially in adversarial/gating... as a general model, I can agree, but as a coding model, they are not bad, comparable to maybe Opus 4.5 in real usage which is quite impressive.

▲

villish 5 hours ago | parent | next [-]

I use GLM or DS4 to help me draft a better initial prompt with more information that I then give to Sonnet 5/Fable/GPT5.5. While benchmarks show the open models close to frontier level, my experience with them is drastically different. I have high confidence that Fable or GPT will 1 shot solutions.

At least with low level programming languages. They're all very good for webdev stuff.

▲

llmslave 5 hours ago | parent | prev [-]

yeah but why waste your time on these models, just use the one that gets the better results

▲

nicoburns 5 hours ago | parent | next [-]

I actively prefer GLM-5.2 for some tasks. For simple tasks the results are just as good as e.g. Opus, and it produces results significantly faster.

▲

9183726518 5 hours ago | parent | prev | next [-]

Because you can get them from more trustworthy providers or with hardware encryption.

	▲	llmslave 5 hours ago \| parent [-]
		i trust anthropic/openai with my data far more than some random startup.

▲

somenameforme 5 hours ago | parent | prev [-]

I was going to respond until I saw your account name lol.

	▲	llmslave 4 hours ago \| parent [-]
		haha i outsource my thinking to the smartest model