I always tell coworkers if they're gonna use Claude to just stick to only Opus and Fable. Sonnet is a waste of time that does a bad job at a bad price.

DeepSeek V4.1 Flash may be chatty but it's cheap, fast, and reliable. I'm not sure what the upside of Sonnet is supposed to be. Right now it feels like a trap.

▲

velcrovan an hour ago | parent | next [-]

Sure, but the fact that Opus 5.5 was such a huge leap over Opus 5 (and Fable 5.1 for that matter) means that it's worth revisiting your priors on a new Sonnet.

▲

eli an hour ago | parent | prev [-]

Hopefully some faster providers will start offering mimo-v2.6-pro because it's cheaper and benchmarks better than Deepseek

▲

jchw an hour ago | parent [-]

Theoretically but I've used DeepSeek V4.1 Flash for several hundred millions of tokens already and it chews through tokens but it is surprisingly good at making it to the end.

MiMo V2.6 Pro I want to love, but I've hit three deathloops in a row. Either my luck is catastrophically bad, or someone needs to patch vLLM or something.

I am sure DeepSeek V4.1 Flash can deathloop, too, but so far it feels less prone to it than other models I've tried like GLM 5.3 Flash so, I'm impressed so far.

I always wonder what the deal with these failure modes are. Google, OpenAI and Anthropic seem to have found good enough workarounds, and I am surprised I don't hear more people talking about them. I thought maybe it was shitty broken providers on OpenRouter, but then I started making presets just for using only the upstream provider and found that no, really, the models do fail that way.

Which is a shame because on paper MiMo V2.6 Pro seems strong, but I haven't gotten through a hard task with it yet.

	▲	eli an hour ago \| parent [-]
		I read they identified a training bug and were going to push out an updated release to fix the looping. I really like it overall. GLM 5.3 Flash is also very good. I think a little smarter and a little more expensive.