Nous Research Releases Open-Source Programming Model NousCoder-14B, Competing with Claude Code Moment
NousCoder-14B is an open-source competitive programming model developed by Nous Research based on Qwen3-14B and trained using verifiable reward reinforcement learning, achieving a 67.87% Pass@1 score on LiveCodeBench v6. This paper outlines its training stack (Atropos, DAPO, Modal), the differences in product form between it and Claude Code, and provides key points for local deployment with Transformers and Ollama. The 67.87% score is the official stated metric, and high scores on algorithm benchmarks do not equate to repository-level Agent capabilities; the open-source weights and complete RL pipeline are the long-term value of this release for developers.
Read More"PaddlePaddle from Beginner to Alchemy" - Part 7: Reinforcement Learning
Your tutorial provides a detailed introduction to implementing a Deep Q-Network (DQN) using PaddlePaddle to play a small game. Below is a summary of your documentation and some supplementary suggestions: ### Document Summary 1. **Environment Setup**: You have explained how to install and configure PaddlePaddle to ensure the relevant code can run successfully. 2. **Project Introduction**: You have elaborated on how to use PaddlePaddle to implement a simple reinforcement learning model for playing a small game (e.g., an Atari game). 3. **Code Implementation** (Note: The original text cuts off here, so the translation reflects the visible content)
Read More