# Open R1: Update #4

DevFeed: [Open R1: Update #4](<https://devfeed.tech/articles/open-r1-update-4-7425.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/open-r1/update-4>)

Author: Leandro von Werra; Vaibhav Srivastav; Daniel Vila; Yacine Jernite

Published: 2025-03-26T18:47:29Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [deepseek](<https://devfeed.tech/topics/deepseek.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [Code](<https://devfeed.tech/topics/code.md>), [coding](<https://devfeed.tech/topics/coding.md>), [math](<https://devfeed.tech/topics/math.md>), [post-training](<https://devfeed.tech/topics/post-training.md>), [Front end](<https://devfeed.tech/topics/frontend.md>)

Tags: [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [deepseek](<https://devfeed.tech/tags/deepseek.md>), [function-calling](<https://devfeed.tech/tags/function-calling.md>), [math](<https://devfeed.tech/tags/math.md>), [post-training](<https://devfeed.tech/tags/post-training.md>), [release](<https://devfeed.tech/tags/release.md>), [update](<https://devfeed.tech/tags/update.md>)

## AI overview

The article reports on a new DeepSeek model that updates DeepSeek-V3, retains its architecture, and adopts an MIT license. It describes improvements in instruction following, coding, mathematics, front-end web development, writing, search, and function calling, supported by stronger benchmark results.

## Source excerpt

This week, a new model from DeepSeek silently landed on the Hub. It's an updated version of DeepSeek-V3, the base model underlying the R1 reasoning model. There isn't much information shared yet on this new model, but we do know a few things! The model has the same architecture as the original DeepSeek-V3 and now also comes with an MIT license, while the previous V3 model had a custom model license.