We introduce
NousCoder-14B
, a competitive programming model post-trained on
Qwen3-14B
via reinforcement learning.
On LiveCodeBench v6 (08/01/2024 - 05/01/2025), we achieve a Pass@1 accuracy of 67.87%, up 7.08% from the baseline Pass@1 accuracy of 60.79%
of Qwen3-14B. We trained on 24k verifiable coding problems using 48 B200s over the course of four days.
Acknowledgements
I would like to thank my mentor, Roger Jin, Dakota Mahan, Teknium, and others at the Nous Research team for their invaluable support throughout this project. I would also like to thank Together AI and Agentica for their immensely helpful blog posts on DeepCoder-14B. Finally, thank you to Modal and Lambda for their generous support by providing me with credits.
Runs of NousResearch NousCoder-14B on huggingface.co
462
Total runs
0
24-hour runs
-1
3-day runs
-4
7-day runs
-634
30-day runs
More Information About NousCoder-14B huggingface.co Model
NousCoder-14B huggingface.co is an AI model on huggingface.co that provides NousCoder-14B's model effect (), which can be used instantly with this NousResearch NousCoder-14B model. huggingface.co supports a free trial of the NousCoder-14B model, and also provides paid use of the NousCoder-14B. Support call NousCoder-14B model through api, including Node.js, Python, http.
NousCoder-14B huggingface.co is an online trial and call api platform, which integrates NousCoder-14B's modeling effects, including api services, and provides a free online trial of NousCoder-14B, you can try NousCoder-14B online for free by clicking the link below.
NousResearch NousCoder-14B online free url in huggingface.co:
NousCoder-14B is an open source model from GitHub that offers a free installation service, and any user can find NousCoder-14B on GitHub to install. At the same time, huggingface.co provides the effect of NousCoder-14B install, users can directly use NousCoder-14B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.