Muse Spark

DeepSeek-V3.2 is a next-generation open large language model designed for efficient reasoning, complex problem solving, and advanced agentic behavior. It introduces DeepSeek Sparse Attention (DSA), a long-context attention mechanism that dramatically reduces computation while preserving performance. The model is trained with a scalable reinforcement learning framework, allowing it to achieve results competitive with GPT-5 and even surpass it in its Speciale variant. DeepSeek-V3.2 also includes a large-scale agent task synthesis pipeline that generates structured reasoning and tool-use demonstrations for post-training. The model features an updated chat template with new tool-calling logic and the optional developer role for agent workflows. With gold-medal performance in the IMO and IOI 2025 competitions, DeepSeek-V3.2 demonstrates elite reasoning capabilities for both research and applied AI scenarios.

Command A+ is Cohere’s fastest and most powerful language model yet, an open-source enterprise workhorse built for complex reasoning, multimodal and multilingual agentic tasks, and efficient private deployment. It is a sparse mixture-of-experts model with 218B total parameters and 25B active parameters, designed for high-performance agentic workflows with minimal compute overhead. Command A+ unifies capabilities from across the Command family into one scalable model, supporting text, image, reasoning, and tool use with a 128K input context, 64K max generation, and support for 48 languages. It is optimized for reasoning, agentic workflows, RAG, multilingual work, and multimodal document processing, with support for vLLM and Transformers. Compared with earlier Command A models, it improves enterprise workload performance across multimodal understanding, retrieval, long-horizon tasks, complex reasoning, coding, translation, and document understanding.