Introducing North Mini Code: Cohere’s First Model For Developers

Hugging Face outlined updates on Introducing North Mini Code: Cohere’s First Model For Developers: introducing North Mini Code: Cohere’s First Model For Developers

Figure 1: North Mini Code’s performance in agentic coding tasks and complex code generation benchmarks, compared to leading open-source models of similar size. See here for the details of our benchmarking methodology. North Mini Code is optimized for complex software engineering workflows, terminal-based agentic tasks, and high-quality code generation. On Artificial Analysis’ Coding Index, North Mini Code achieves a score of 33.4, outperforming Qwen3.5 (35B-A3B), Gemma 4 (26B-A4B), Devstral Small 2 (24B Dense), and even substantially larger models such as Nemotron 3 Super (120B-A12B), Mistral Small 4 (119B-A6B), and Devstral 2 (123B).1 It ranks among the strongest open-source coding models in its size class. Try North Mini Code in OpenCode Real-world code agents depend on model quality and robustness across agent harnesses. We trained North Mini Code using multiple scaffolds rather than optimizing for a single one. This approach enables North Mini Code to serve as a reliable foundation for coding agents such as OpenCode. Figure 2: North Mini Code is a Mixture-of-Experts Transformer decoder with interleaved sliding-window self-attention and full self-attention. North Mini Code is a decoder-only Transformer-based sparse Mixture-of-Experts model. It uses our efficient attention implementation, interleaved between sliding-window attention with RoPE and global attention with no positional embeddings, in a 3:1 ratio [1]. The feed-forward block is an MoE block with 128 experts, of which 8 are activated per token. Each expert block is an FFN block with SwiGLU activation. The router applies a sigmoid activation function to the logits before the top-k selection. We also use a single dense layer before the sparse layers. Figure 3: The post-training pipeline is made up of two phases of supervised fine-tuning (SFT) and a phase of agentic reinforcement learning with verifiable rewards (RLVR) targeting software engineering and terminal tasks.