Open weight models are extremely capable. The stats the article relies on are not the most accurate since open weight models are known for higher verbosity and lack of efficiency. Although if you're self hosting open weights that's a different story all together.
Deepseek 4.1 Flash 1017 has been pretty good for coding, I agree. It doesn't seem to do documentation as well, things like requirements, specifications, implementation plans. Here I still use GLM5.3 for a better outcome. I also use both models as adversarial batteries to check the work of each other.
Having said that, 1017 has been great in saving money. It's available generally much cheaper than GLM5.3, and I think it delivers >90% of the capability.
Open weight models are extremely capable. The stats the article relies on are not the most accurate since open weight models are known for higher verbosity and lack of efficiency. Although if you're self hosting open weights that's a different story all together.
New deep seek 4.1 has done the majority of coding tasks ive thrown at it no problem
Deepseek 4.1 Flash 1017 has been pretty good for coding, I agree. It doesn't seem to do documentation as well, things like requirements, specifications, implementation plans. Here I still use GLM5.3 for a better outcome. I also use both models as adversarial batteries to check the work of each other.
Having said that, 1017 has been great in saving money. It's available generally much cheaper than GLM5.3, and I think it delivers >90% of the capability.
Will have to try this review stratergy with GLM, Thanks for sharing
[flagged]
[flagged]
[flagged]