Open models can do 90 percent of agentic work at a twentieth of the cost

Posted by Betelbuddy on Tuesday November 03, 2026 @02:46AM
from the theregister.com dept.

https://www.theregister.com/ai-and-ml/2026/11/03/open-models-can-do-90-percent-of-agentic-work-at-a-twentieth-of-the-cost-of-a-frontier-llm-gartner/5307132

( 4 comments | on HN )

Re:Open models can do 90 percent of agentic work at a twenti... by Northernator11 on Tuesday November 03, 2026 @04:50AM (#50349982)

New deep seek 4.1 has done the majority of coding tasks ive thrown at it no problem

[ Parent | on HN ]

Re:Open models can do 90 percent of agentic work at a twenti... by phillc73 on Tuesday November 03, 2026 @05:30AM (#50350227)

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.

[ Parent | on HN ]

Re:Open models can do 90 percent of agentic work at a twenti... by Northernator11 on Tuesday November 03, 2026 @09:59AM (#50352826)

Will have to try this review stratergy with GLM, Thanks for sharing

[ Parent | on HN ]

Re:Open models can do 90 percent of agentic work at a twenti... by elijahglass on Tuesday November 03, 2026 @08:44AM (#50351899)

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.

[ Parent | on HN ]