Alternatives to Mixtral 8x7B

MiniMax M3 is a frontier open-weight AI model built for coding, agentic work, multimodal understanding, and ultra-long-context tasks. The model supports up to a 1 million token context window, allowing it to work across large codebases, long documents, logs, project histories, and complex task environments. MiniMax M3 introduces MiniMax Sparse Attention, a sparse attention architecture designed to make long-context processing more efficient. The model is natively multimodal, with training that supports deeper semantic fusion across text, image, and video inputs. It is designed to support software engineering tasks, repository analysis, terminal-style work, browser-style retrieval, tool use, and autonomous workflows. MiniMax M3 has a mixture-of-experts architecture with hundreds of billions of total parameters and a smaller activated parameter count for more efficient inference. Developers can use it for AI coding assistants, workflow automation, research agents, document analysis, visual reasoning, and enterprise AI systems. Its long-context capability makes it especially useful when tasks require many files, references, instructions, or interaction histories to stay available at once. MiniMax M3 helps teams build more capable AI agents that can understand larger problems, work across multiple modalities, and execute complex tasks with stronger context awareness.

Inkling is Thinking Machines’ open-weights foundation model built for customization, multimodal reasoning, and agentic AI workflows. The model uses a Mixture-of-Experts architecture with 975 billion total parameters and 41 billion active parameters, making it large in capacity while activating only a subset of experts per token. Inkling supports up to a 1 million token context window and was pretrained on 45 trillion tokens spanning text, images, audio, and video. It is designed as a broad generalist model with strengths across coding, reasoning, instruction following, factuality, tool use, vision, audio understanding, forecasting, and safety. Developers can tune its thinking effort to trade off latency, cost, and performance, which is useful for production systems that need efficient reasoning at scale. Inkling can be fine-tuned on Tinker, tested in the Inkling Playground, and deployed through partners such as TogetherAI, Fireworks, Modal, Databricks, Baseten, vLLM, SGLang, llama.cpp, and Hugging Face transformers. The model can generate applications, operate tools, create styled artifacts, reason over visual and audio inputs, and support long refinement loops for collaborative work. Thinking Machines also previewed Inkling-Small, a lighter Mixture-of-Experts model with 276 billion total parameters and 12 billion active parameters for lower-cost and lower-latency workloads. By combining open weights, multimodal training, agentic capabilities, efficient reasoning, and fine-tuning support, Inkling gives builders a flexible AI foundation for specialized products and workflows.

Cohere has introduced Command R+, its latest large language model designed to excel in conversational interactions and manage long-context tasks with remarkable efficiency. This model is tailored for organizations looking to transition from experimental phases to full-scale production. We suggest utilizing Command R+ for workflows that require advanced retrieval-augmented generation capabilities and the use of multiple tools in a sequence. Conversely, Command R is well-suited for less complicated retrieval-augmented generation tasks and scenarios involving single-step tool usage, particularly when cost-effectiveness is a key factor in decision-making.

The outputs generated by Command’s model are accompanied by precise citations that help reduce the chances of misinformation while providing additional context drawn from the original sources. Command is capable of creating product descriptions, assisting in email composition, proposing sample press releases, and much more. You can engage Command with multiple inquiries about a document to categorize it, retrieve specific information, or address general questions pertaining to the content. While answering a handful of questions about a single document can save valuable time, applying this process to thousands of documents can lead to significant time savings for a business. This suite of scalable models achieves a remarkable balance between high efficiency and robust accuracy, empowering organizations to transition from experimental stages to fully operational AI solutions. By leveraging these capabilities, companies can enhance their productivity and streamline their workflows effectively.

Jamba stands out as the most potent and effective long context model, specifically designed for builders while catering to enterprise needs. With superior latency compared to other leading models of similar sizes, Jamba boasts a remarkable 256k context window, the longest that is openly accessible. Its innovative Mamba-Transformer MoE architecture focuses on maximizing cost-effectiveness and efficiency. Key features available out of the box include function calls, JSON mode output, document objects, and citation mode, all designed to enhance user experience. Jamba 1.5 models deliver exceptional performance throughout their extensive context window and consistently achieve high scores on various quality benchmarks. Enterprises can benefit from secure deployment options tailored to their unique requirements, allowing for seamless integration into existing systems. Jamba can be easily accessed on our robust SaaS platform, while deployment options extend to strategic partners, ensuring flexibility for users. For organizations with specialized needs, we provide dedicated management and continuous pre-training, ensuring that every client can leverage Jamba’s capabilities to the fullest. This adaptability makes Jamba a prime choice for enterprises looking for cutting-edge solutions.

DeepSeek Coder is an innovative software solution poised to transform the realm of data analysis and programming. By harnessing state-of-the-art machine learning techniques and natural language processing, it allows users to effortlessly incorporate data querying, analysis, and visualization into their daily tasks. The user-friendly interface caters to both beginners and seasoned developers, making the writing, testing, and optimization of code a straightforward process. Among its impressive features are real-time syntax validation, smart code suggestions, and thorough debugging capabilities, all aimed at enhancing productivity in coding. Furthermore, DeepSeek Coder’s proficiency in deciphering intricate data sets enables users to extract valuable insights and develop advanced data-centric applications with confidence. Ultimately, its combination of powerful tools and ease of use positions DeepSeek Coder as an essential asset for anyone engaged in data-driven projects.

On September 17, 2024, Mistral AI revealed a series of significant updates designed to improve both the accessibility and efficiency of their AI products. Among these updates was the introduction of a complimentary tier on "La Plateforme," their serverless platform that allows for the tuning and deployment of Mistral models as API endpoints, which gives developers a chance to innovate and prototype at zero cost. In addition, Mistral AI announced price reductions across their complete model range, highlighted by a remarkable 50% decrease for Mistral Nemo and an 80% cut for Mistral Small and Codestral, thereby making advanced AI solutions more affordable for a wider audience. The company also launched Mistral Small v24.09, a model with 22 billion parameters that strikes a favorable balance between performance and efficiency, making it ideal for various applications such as translation, summarization, and sentiment analysis. Moreover, they released Pixtral 12B, a vision-capable model equipped with image understanding features, for free on "Le Chat," allowing users to analyze and caption images while maintaining strong text-based performance. This suite of updates reflects Mistral AI's commitment to democratizing access to powerful AI technologies for developers everywhere.

Mistral Medium 3.1 represents a significant advancement in multimodal foundation models, launched in August 2025, and is engineered to provide superior reasoning, coding, and multimodal functionalities while significantly simplifying deployment processes and minimizing costs. This model is an evolution of the highly efficient Mistral Medium 3 architecture, which is celebrated for delivering top-tier performance at a fraction of the cost—up to eight times less than many leading large models—while also improving tone consistency, responsiveness, and precision across a variety of tasks and modalities. It is designed to operate effectively in hybrid environments, including on-premises and virtual private cloud systems, and competes strongly with high-end models like Claude Sonnet 3.7, Llama 4 Maverick, and Cohere Command A. Mistral Medium 3.1 is particularly well-suited for professional and enterprise applications, excelling in areas such as coding, STEM reasoning, and language comprehension across multiple formats. Furthermore, it ensures extensive compatibility with personalized workflows and existing infrastructure, making it a versatile choice for various organizational needs. As businesses seek to leverage AI in more complex scenarios, Mistral Medium 3.1 stands out as a robust solution to meet those challenges.

Introducing a remarkable family of compact language models (SLMs) that deliver exceptional performance while being cost-effective and low in latency. These models are designed to enhance AI functionalities, decrease resource consumption, and promote budget-friendly generative AI applications across various platforms. They improve response times in real-time interactions, navigate autonomous systems, and support applications that demand low latency, all critical to user experience. Phi-3 can be deployed in cloud environments, edge computing, or directly on devices, offering unparalleled flexibility for deployment and operations. Developed in alignment with Microsoft AI principles—such as accountability, transparency, fairness, reliability, safety, privacy, security, and inclusiveness—these models ensure ethical AI usage. They also excel in offline environments where data privacy is essential or where internet connectivity is sparse. With an expanded context window, Phi-3 generates outputs that are more coherent, accurate, and contextually relevant, making it an ideal choice for various applications. Ultimately, deploying at the edge not only enhances speed but also ensures that users receive timely and effective responses.

The Mixtral 8x22B represents our newest open model, establishing a new benchmark for both performance and efficiency in the AI sector. This sparse Mixture-of-Experts (SMoE) model activates only 39B parameters from a total of 141B, ensuring exceptional cost efficiency relative to its scale. Additionally, it demonstrates fluency in multiple languages, including English, French, Italian, German, and Spanish, while also possessing robust skills in mathematics and coding. With its native function calling capability, combined with the constrained output mode utilized on la Plateforme, it facilitates the development of applications and the modernization of technology stacks on a large scale. The model's context window can handle up to 64K tokens, enabling accurate information retrieval from extensive documents. We prioritize creating models that maximize cost efficiency for their sizes, thereby offering superior performance-to-cost ratios compared to others in the community. The Mixtral 8x22B serves as a seamless extension of our open model lineage, and its sparse activation patterns contribute to its speed, making it quicker than any comparable dense 70B model on the market. Furthermore, its innovative design positions it as a leading choice for developers seeking high-performance solutions.

Pixtral Large is an expansive multimodal model featuring 124 billion parameters, crafted by Mistral AI and enhancing their previous Mistral Large 2 framework. This model combines a 123-billion-parameter multimodal decoder with a 1-billion-parameter vision encoder, allowing it to excel in the interpretation of various content types, including documents, charts, and natural images, all while retaining superior text comprehension abilities. With the capability to manage a context window of 128,000 tokens, Pixtral Large can efficiently analyze at least 30 high-resolution images at once. It has achieved remarkable results on benchmarks like MathVista, DocVQA, and VQAv2, outpacing competitors such as GPT-4o and Gemini-1.5 Pro. Available for research and educational purposes under the Mistral Research License, it also has a Mistral Commercial License for business applications. This versatility makes Pixtral Large a valuable tool for both academic research and commercial innovations.

Qwen2 represents a collection of extensive language models crafted by the Qwen team at Alibaba Cloud. This series encompasses a variety of models, including base and instruction-tuned versions, with parameters varying from 0.5 billion to an impressive 72 billion, showcasing both dense configurations and a Mixture-of-Experts approach. The Qwen2 series aims to outperform many earlier open-weight models, including its predecessor Qwen1.5, while also striving to hold its own against proprietary models across numerous benchmarks in areas such as language comprehension, generation, multilingual functionality, programming, mathematics, and logical reasoning. Furthermore, this innovative series is poised to make a significant impact in the field of artificial intelligence, offering enhanced capabilities for a diverse range of applications.

Tülu 3 is a cutting-edge language model created by the Allen Institute for AI (Ai2) that aims to improve proficiency in fields like knowledge, reasoning, mathematics, coding, and safety. It is based on the Llama 3 Base and undergoes a detailed four-stage post-training regimen: careful prompt curation and synthesis, supervised fine-tuning on a wide array of prompts and completions, preference tuning utilizing both off- and on-policy data, and a unique reinforcement learning strategy that enhances targeted skills through measurable rewards. Notably, this open-source model sets itself apart by ensuring complete transparency, offering access to its training data, code, and evaluation tools, thus bridging the performance divide between open and proprietary fine-tuning techniques. Performance assessments reveal that Tülu 3 surpasses other models with comparable sizes, like Llama 3.1-Instruct and Qwen2.5-Instruct, across an array of benchmarks, highlighting its effectiveness. The continuous development of Tülu 3 signifies the commitment to advancing AI capabilities while promoting an open and accessible approach to technology.

Mistral Large 3 pushes open-source AI into frontier territory with a massive sparse MoE architecture that activates 41B parameters per token while maintaining a highly efficient 675B total parameter design. It sets a new performance standard by combining long-context reasoning, multilingual fluency across 40+ languages, and robust multimodal comprehension within a single unified model. Trained end-to-end on thousands of NVIDIA H200 GPUs, it reaches parity with top closed-source instruction models while remaining fully accessible under the Apache 2.0 license. Developers benefit from optimized deployments through partnerships with NVIDIA, Red Hat, and vLLM, enabling smooth inference on A100, H100, and Blackwell-class systems. The model ships in both base and instruct variants, with a reasoning-enhanced version on the way for even deeper analytical capabilities. Beyond general intelligence, Mistral Large 3 is engineered for enterprise customization, allowing organizations to refine the model on internal datasets or domain-specific tasks. Its efficient token generation and powerful multimodal stack make it ideal for coding, document analysis, knowledge workflows, agentic systems, and multilingual communications. With Mistral Large 3, organizations can finally deploy frontier-class intelligence with full transparency, flexibility, and control.

Qwen3.5 represents a major advancement in open-weight multimodal AI models, engineered to function as a native vision-language agent system. Its flagship model, Qwen3.5-397B-A17B, leverages a hybrid architecture that fuses Gated DeltaNet linear attention with a high-sparsity mixture-of-experts framework, allowing only 17 billion parameters to activate during inference for improved speed and cost efficiency. Despite its sparse activation, the full 397-billion-parameter model achieves competitive performance across reasoning, coding, multilingual benchmarks, and complex agent evaluations. The hosted Qwen3.5-Plus version supports a one-million-token context window and includes built-in tool use for search, code interpretation, and adaptive reasoning. The model significantly expands multilingual coverage to 201 languages and dialects while improving encoding efficiency with a larger vocabulary. Native multimodal training enables strong performance in image understanding, video processing, document analysis, and spatial reasoning tasks. Its infrastructure includes FP8 precision pipelines and heterogeneous parallelism to boost throughput and reduce memory consumption. Reinforcement learning at scale enhances multi-step planning and general agent behavior across text and multimodal environments. Overall, Qwen3.5 positions itself as a high-efficiency foundation for autonomous digital agents capable of reasoning, searching, coding, and interacting with complex environments.

Mistral 7B is a language model with 7.3 billion parameters that demonstrates superior performance compared to larger models such as Llama 2 13B on a variety of benchmarks. It utilizes innovative techniques like Grouped-Query Attention (GQA) for improved inference speed and Sliding Window Attention (SWA) to manage lengthy sequences efficiently. Released under the Apache 2.0 license, Mistral 7B is readily available for deployment on different platforms, including both local setups and prominent cloud services. Furthermore, a specialized variant known as Mistral 7B Instruct has shown remarkable capabilities in following instructions, outperforming competitors like Llama 2 13B Chat in specific tasks. This versatility makes Mistral 7B an attractive option for developers and researchers alike.

Qwen3.8-27B is a newly announced 27-billion-parameter model from Alibaba’s Qwen3.8 series, designed as a more compact open-weight alternative to the significantly larger Qwen3.8-Max. The Qwen3.8 generation represents a cutting-edge family of models aimed at enhancing coding capabilities, performing agentic tasks, achieving multimodal comprehension, and managing prolonged autonomous operations. The introduction of the 27B variant aims to provide a size that facilitates more practical local deployment, hands-on experimentation, fine-tuning, and smoother integration into developers' workflows. Qwen has confirmed that this model will be released with open weights, thereby enriching the company’s collection of downloadable mid-sized models tailored for users seeking direct control over their inference and deployment processes. At the time of its announcement, however, Qwen had yet to provide essential information such as the model card, benchmark metrics, architectural specifics, context length, quantization methods, or comprehensive deployment instructions for the 27B version. This lack of detailed guidance raises questions among potential users eager to explore the model's capabilities.

The MiniMax‑M1 model, introduced by MiniMax AI and licensed under Apache 2.0, represents a significant advancement in hybrid-attention reasoning architecture. With an extraordinary capacity for handling a 1 million-token context window and generating outputs of up to 80,000 tokens, it facilitates in-depth analysis of lengthy texts. Utilizing a cutting-edge CISPO algorithm, MiniMax‑M1 was trained through extensive reinforcement learning, achieving completion on 512 H800 GPUs in approximately three weeks. This model sets a new benchmark in performance across various domains, including mathematics, programming, software development, tool utilization, and understanding of long contexts, either matching or surpassing the capabilities of leading models in the field. Additionally, users can choose between two distinct variants of the model, each with a thinking budget of either 40K or 80K, and access the model's weights and deployment instructions on platforms like GitHub and Hugging Face. Such features make MiniMax‑M1 a versatile tool for developers and researchers alike.

GLM-5.1 represents the latest advancement in Z.ai’s GLM series, crafted as a cutting-edge, agent-focused AI model tailored for coding, reasoning, and managing long-term workflows. This iteration builds upon the framework of GLM-5, which employs a Mixture-of-Experts (MoE) architecture to achieve high performance without incurring excessive inference expenses, aligning with a larger initiative towards open-weight models that are accessible to developers. A significant emphasis of GLM-5.1 is on fostering agentic behavior, allowing it to plan, execute, and refine multi-step tasks instead of merely reacting to isolated prompts. Its capabilities are specifically engineered to manage intricate workflows, such as debugging code, exploring repositories, and performing sequential operations while maintaining context over time. In comparison to its predecessors, GLM-5.1 enhances reliability during lengthy interactions, ensuring coherence throughout extended sessions and minimizing failures in multi-step reasoning processes. Overall, this model signifies a leap forward in AI development, particularly in its ability to support complex task management seamlessly.

Llama 4 Behemoth, with 288 billion active parameters, is Meta's flagship AI model, setting new standards for multimodal performance. Outpacing its predecessors like GPT-4.5 and Claude Sonnet 3.7, it leads the field in STEM benchmarks, offering cutting-edge results in tasks such as problem-solving and reasoning. Designed as the teacher model for the Llama 4 series, Behemoth drives significant improvements in model quality and efficiency through distillation. Although still in development, Llama 4 Behemoth is shaping the future of AI with its unparalleled intelligence, particularly in math, image, and multilingual tasks.

Introducing DeepSeek-V3.2-Exp, our newest experimental model derived from V3.1-Terminus, featuring the innovative DeepSeek Sparse Attention (DSA) that enhances both training and inference speed for lengthy contexts. This DSA mechanism allows for precise sparse attention while maintaining output quality, leading to improved performance for tasks involving long contexts and a decrease in computational expenses. Benchmark tests reveal that V3.2-Exp matches the performance of V3.1-Terminus while achieving these efficiency improvements. The model is now fully operational across app, web, and API platforms. Additionally, to enhance accessibility, we have slashed DeepSeek API prices by over 50% effective immediately. During a transition period, users can still utilize V3.1-Terminus via a temporary API endpoint until October 15, 2025. DeepSeek encourages users to share their insights regarding DSA through our feedback portal. Complementing the launch, DeepSeek-V3.2-Exp has been made open-source, with model weights and essential technology—including crucial GPU kernels in TileLang and CUDA—accessible on Hugging Face. We look forward to seeing how the community engages with this advancement.

Qwen3.6 is an advanced AI model from Alibaba that builds on previous Qwen releases with a focus on real-world utility and performance. It is designed as a multimodal large language model capable of understanding and generating text while also processing visual and structured data. The model is optimized for coding tasks, enabling developers to handle complex, repository-level programming workflows. Qwen3.6 uses a mixture-of-experts (MoE) architecture, which activates only a portion of its parameters during inference to improve efficiency. This design allows it to deliver strong performance while reducing computational costs. It is available in both proprietary and open-weight versions, giving developers flexibility in deployment. The model supports integration into enterprise systems and cloud platforms, particularly within Alibaba’s ecosystem. Qwen3.6 also introduces stronger agentic capabilities, allowing it to perform multi-step reasoning and more autonomous task execution. It is designed to handle complex workflows, including engineering, analysis, and decision-making tasks. The model emphasizes stability and responsiveness based on developer feedback. Overall, Qwen3.6 provides a scalable and efficient AI solution for coding, automation, and multimodal applications.

Mistral 3 represents the newest iteration of open-weight AI models developed by Mistral AI, encompassing a diverse range of models that span from compact, edge-optimized versions to a leading large-scale multimodal model. This lineup features three efficient “Ministral 3” models with 3 billion, 8 billion, and 14 billion parameters, tailored for deployment on devices with limited resources, such as laptops, drones, or other edge devices. Additionally, there is the robust “Mistral Large 3,” which is a sparse mixture-of-experts model boasting a staggering 675 billion total parameters, with 41 billion of them being active. These models are designed to handle multimodal and multilingual tasks, excelling not only in text processing but also in image comprehension, and they have showcased exceptional performance on general queries, multilingual dialogues, and multimodal inputs. Furthermore, both the base and instruction-fine-tuned versions are made available under the Apache 2.0 license, allowing for extensive customization and integration into various enterprise and open-source initiatives. This flexibility in licensing encourages innovation and collaboration among developers and organizations alike.

Kimi K2 represents a cutting-edge series of open-source large language models utilizing a mixture-of-experts (MoE) architecture, with a staggering 1 trillion parameters in total and 32 billion activated parameters tailored for optimized task execution. Utilizing the Muon optimizer, it has been trained on a substantial dataset of over 15.5 trillion tokens, with its performance enhanced by MuonClip’s attention-logit clamping mechanism, resulting in remarkable capabilities in areas such as advanced knowledge comprehension, logical reasoning, mathematics, programming, and various agentic operations. Moonshot AI offers two distinct versions: Kimi-K2-Base, designed for research-level fine-tuning, and Kimi-K2-Instruct, which is pre-trained for immediate applications in chat and tool interactions, facilitating both customized development and seamless integration of agentic features. Comparative benchmarks indicate that Kimi K2 surpasses other leading open-source models and competes effectively with top proprietary systems, particularly excelling in coding and intricate task analysis. Furthermore, it boasts a generous context length of 128 K tokens, compatibility with tool-calling APIs, and support for industry-standard inference engines, making it a versatile option for various applications. The innovative design and features of Kimi K2 position it as a significant advancement in the field of artificial intelligence language processing.

Qwen2.5-Max is an advanced Mixture-of-Experts (MoE) model created by the Qwen team, which has been pretrained on an extensive dataset of over 20 trillion tokens and subsequently enhanced through methods like Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF). Its performance in evaluations surpasses that of models such as DeepSeek V3 across various benchmarks, including Arena-Hard, LiveBench, LiveCodeBench, and GPQA-Diamond, while also achieving strong results in other tests like MMLU-Pro. This model is available through an API on Alibaba Cloud, allowing users to easily integrate it into their applications, and it can also be interacted with on Qwen Chat for a hands-on experience. With its superior capabilities, Qwen2.5-Max represents a significant advancement in AI model technology.

We are thrilled to present DBRX, a versatile open LLM developed by Databricks. This innovative model achieves unprecedented performance on a variety of standard benchmarks, setting a new benchmark for existing open LLMs. Additionally, it equips both the open-source community and enterprises crafting their own LLMs with features that were once exclusive to proprietary model APIs; our evaluations indicate that it outperforms GPT-3.5 and competes effectively with Gemini 1.0 Pro. Notably, it excels as a code model, outperforming specialized counterparts like CodeLLaMA-70B in programming tasks, while also demonstrating its prowess as a general-purpose LLM. The remarkable quality of DBRX is complemented by significant enhancements in both training and inference efficiency. Thanks to its advanced fine-grained mixture-of-experts (MoE) architecture, DBRX elevates the efficiency of open models to new heights. In terms of inference speed, it can be twice as fast as LLaMA2-70B, and its total and active parameter counts are approximately 40% of those in Grok-1, showcasing its compact design without compromising capability. This combination of speed and size makes DBRX a game-changer in the landscape of open AI models.

Falcon-40B is a causal decoder-only model consisting of 40 billion parameters, developed by TII and trained on 1 trillion tokens from RefinedWeb, supplemented with carefully selected datasets. It is distributed under the Apache 2.0 license. Why should you consider using Falcon-40B? This model stands out as the leading open-source option available, surpassing competitors like LLaMA, StableLM, RedPajama, and MPT, as evidenced by its ranking on the OpenLLM Leaderboard. Its design is specifically tailored for efficient inference, incorporating features such as FlashAttention and multiquery capabilities. Moreover, it is offered under a flexible Apache 2.0 license, permitting commercial applications without incurring royalties or facing restrictions. It's important to note that this is a raw, pretrained model and is generally recommended to be fine-tuned for optimal performance in most applications. If you need a version that is more adept at handling general instructions in a conversational format, you might want to explore Falcon-40B-Instruct as a potential alternative.

Introducing an open-source AI model that can be fine-tuned, distilled, and deployed across various platforms. Our newest instruction-tuned model comes in three sizes: 8B, 70B, and 405B, giving you options to suit different needs. With our open ecosystem, you can expedite your development process using a diverse array of tailored product offerings designed to meet your specific requirements. You have the flexibility to select between real-time inference and batch inference services according to your project's demands. Additionally, you can download model weights to enhance cost efficiency per token while fine-tuning for your application. Improve performance further by utilizing synthetic data and seamlessly deploy your solutions on-premises or in the cloud. Take advantage of Llama system components and expand the model's capabilities through zero-shot tool usage and retrieval-augmented generation (RAG) to foster agentic behaviors. By utilizing 405B high-quality data, you can refine specialized models tailored to distinct use cases, ensuring optimal functionality for your applications. Ultimately, this empowers developers to create innovative solutions that are both efficient and effective.

GLM-5 is a next-generation open-source foundation model from Z.ai designed to push the boundaries of agentic engineering and complex task execution. Compared to earlier versions, it significantly expands parameter count and training data, while introducing DeepSeek Sparse Attention to optimize inference efficiency. The model leverages a novel asynchronous reinforcement learning framework called slime, which enhances training throughput and enables more effective post-training alignment. GLM-5 delivers leading performance among open-source models in reasoning, coding, and general agent benchmarks, with strong results on SWE-bench, BrowseComp, and Vending Bench 2. Its ability to manage long-horizon simulations highlights advanced planning, resource allocation, and operational decision-making skills. Beyond benchmark performance, GLM-5 supports real-world productivity by generating fully formatted documents such as .docx, .pdf, and .xlsx files. It integrates with coding agents like Claude Code and OpenClaw, enabling cross-application automation and collaborative agent workflows. Developers can access GLM-5 via Z.ai’s API, deploy it locally with frameworks like vLLM or SGLang, or use it through an interactive GUI environment. The model is released under the MIT License, encouraging broad experimentation and adoption. Overall, GLM-5 represents a major step toward practical, work-oriented AI systems that move beyond chat into full task execution.

Xiaomi MiMo-V2.5 is a next-generation open-source AI model that combines agentic intelligence with multimodal capabilities. It is designed to process and understand text, images, and audio within a single architecture. The model uses a sparse Mixture-of-Experts framework with a large parameter count to deliver efficient and scalable performance. It supports a context window of up to one million tokens, allowing it to handle long and complex workflows. MiMo-V2.5 integrates visual and audio encoders to improve perception and cross-modal reasoning. It is capable of performing tasks such as coding, reasoning, and multimodal analysis with strong accuracy. Benchmark results show competitive performance compared to leading AI models in both agentic and multimodal tasks. The model is optimized for token efficiency, balancing performance with lower computational cost. It is designed for real-world applications that require both reasoning and perception. Xiaomi has open-sourced the model, making it accessible for developers and researchers. By combining multimodality, scalability, and efficiency, MiMo-V2.5 pushes forward the development of advanced AI systems.

We are excited to unveil Codestral, our inaugural code generation model. This open-weight generative AI system is specifically crafted for tasks related to code generation, enabling developers to seamlessly write and engage with code via a unified instruction and completion API endpoint. As it becomes proficient in both programming languages and English, Codestral is poised to facilitate the creation of sophisticated AI applications tailored for software developers. With a training foundation that encompasses a wide array of over 80 programming languages—ranging from widely-used options like Python, Java, C, C++, JavaScript, and Bash to more niche languages such as Swift and Fortran—Codestral ensures a versatile support system for developers tackling various coding challenges and projects. Its extensive language capabilities empower developers to confidently navigate different coding environments, making Codestral an invaluable asset in the programming landscape.

Introducing the next iteration of our open-source large language model, this version features model weights along with initial code for the pretrained and fine-tuned Llama language models, which span from 7 billion to 70 billion parameters. The Llama 2 pretrained models have been developed using an impressive 2 trillion tokens and offer double the context length compared to their predecessor, Llama 1. Furthermore, the fine-tuned models have been enhanced through the analysis of over 1 million human annotations. Llama 2 demonstrates superior performance against various other open-source language models across multiple external benchmarks, excelling in areas such as reasoning, coding capabilities, proficiency, and knowledge assessments. For its training, Llama 2 utilized publicly accessible online data sources, while the fine-tuned variant, Llama-2-chat, incorporates publicly available instruction datasets along with the aforementioned extensive human annotations. Our initiative enjoys strong support from a diverse array of global stakeholders who are enthusiastic about our open approach to AI, including companies that have provided valuable early feedback and are eager to collaborate using Llama 2. The excitement surrounding Llama 2 signifies a pivotal shift in how AI can be developed and utilized collectively.

MiMo-V2-Flash is a large language model created by Xiaomi that utilizes a Mixture-of-Experts (MoE) framework, combining remarkable performance with efficient inference capabilities. With a total of 309 billion parameters, it activates just 15 billion parameters during each inference, allowing it to effectively balance reasoning quality and computational efficiency. This model is well-suited for handling lengthy contexts, making it ideal for tasks such as long-document comprehension, code generation, and multi-step workflows. Its hybrid attention mechanism integrates both sliding-window and global attention layers, which helps to minimize memory consumption while preserving the ability to understand long-range dependencies. Additionally, the Multi-Token Prediction (MTP) design enhances inference speed by enabling the simultaneous processing of batches of tokens. MiMo-V2-Flash boasts impressive generation rates of up to approximately 150 tokens per second and is specifically optimized for applications that demand continuous reasoning and multi-turn interactions. The innovative architecture of this model reflects a significant advancement in the field of language processing.

Opus, recognized as our most advanced model, surpasses its competitors in numerous widely-used evaluation benchmarks for artificial intelligence, including assessments of undergraduate expert knowledge (MMLU), graduate-level reasoning (GPQA), fundamental mathematics (GSM8K), and others. Its performance approaches human-like comprehension and fluency in handling intricate tasks, positioning it at the forefront of general intelligence advancements. Furthermore, all Claude 3 models demonstrate enhanced abilities in analysis and prediction, sophisticated content creation, programming code generation, and engaging in conversations in various non-English languages such as Spanish, Japanese, and French, showcasing their versatility in communication.

MAI-Thinking-1 represents Microsoft AI's advanced reasoning model, specifically engineered to tackle intricate and significant challenges, exhibiting superior reasoning capabilities alongside robust software engineering performance within its category. This model features a configuration of 35 billion active parameters and roughly 1 trillion total parameters as a sparse Mixture of Experts, allowing it to maintain a more streamlined inference footprint compared to much larger alternatives while still achieving performance comparable to leading models on essential software engineering benchmarks. Microsoft developed MAI-Thinking-1 from the ground up, utilizing high-quality, enterprise-grade, commercially licensed data, ensuring that its abilities are acquired rather than derived from third-party models. Integral to Microsoft AI’s innovative Hill-Climbing Machine, this model benefits from a collaborative development process designed for ongoing and reliable enhancements throughout all stages of model creation. MAI-Thinking-1 is particularly suited for agentic coding environments, as it is capable of reading code, modifying files, executing tests, detecting errors, and recovering from mistakes made along the way. This ability to adapt and learn in real-time makes it a valuable asset for developers seeking efficiency and reliability in their projects.

EXAONE Deep represents a collection of advanced language models that are enhanced for reasoning, created by LG AI Research, and come in sizes of 2.4 billion, 7.8 billion, and 32 billion parameters. These models excel in a variety of reasoning challenges, particularly in areas such as mathematics and coding assessments. Significantly, the EXAONE Deep 2.4B model outshines other models of its size, while the 7.8B variant outperforms both open-weight models of similar dimensions and the proprietary reasoning model known as OpenAI o1-mini. Furthermore, the EXAONE Deep 32B model competes effectively with top-tier open-weight models in the field. The accompanying repository offers extensive documentation that includes performance assessments, quick-start guides for leveraging EXAONE Deep models with the Transformers library, detailed explanations of quantized EXAONE Deep weights formatted in AWQ and GGUF, as well as guidance on how to run these models locally through platforms like llama.cpp and Ollama. Additionally, this resource serves to enhance user understanding and accessibility to the capabilities of EXAONE Deep models.

LFM-3B offers outstanding performance relative to its compact size, securing its top position among models with 3 billion parameters, hybrids, and RNNs, while surpassing earlier generations of 7 billion and 13 billion parameter models. In addition, it matches the performance of Phi-3.5-mini across several benchmarks, all while being 18.4% smaller in size. This makes LFM-3B the perfect option for mobile applications and other edge-based text processing needs, illustrating its versatility and efficiency in a variety of settings.

OpenAI's o1 series introduces a new generation of AI models specifically developed to enhance reasoning skills. Among these models are o1-preview and o1-mini, which utilize an innovative reinforcement learning technique that encourages them to dedicate more time to "thinking" through various problems before delivering solutions. This method enables the o1 models to perform exceptionally well in intricate problem-solving scenarios, particularly in fields such as coding, mathematics, and science, and they have shown to surpass earlier models like GPT-4o in specific benchmarks. The o1 series is designed to address challenges that necessitate more profound cognitive processes, representing a pivotal advancement toward AI systems capable of reasoning in a manner similar to humans. As it currently stands, the series is still undergoing enhancements and assessments, reflecting OpenAI's commitment to refining these technologies further. The continuous development of the o1 models highlights the potential for AI to evolve and meet more complex demands in the future.

Llama 4 Scout is an advanced multimodal AI model with 17 billion active parameters, offering industry-leading performance with a 10 million token context length. This enables it to handle complex tasks like multi-document summarization and detailed code reasoning with impressive accuracy. Scout surpasses previous Llama models in both text and image understanding, making it an excellent choice for applications that require a combination of language processing and image analysis. Its powerful capabilities in long-context tasks and image-grounding applications set it apart from other models in its class, providing superior results for a wide range of industries.

This repository showcases the research preview of LongLLaMA, an advanced large language model that can manage extensive contexts of up to 256,000 tokens or potentially more. LongLLaMA is developed on the OpenLLaMA framework and has been fine-tuned utilizing the Focused Transformer (FoT) technique. The underlying code for LongLLaMA is derived from Code Llama. We are releasing a smaller 3B base variant of the LongLLaMA model, which is not instruction-tuned, under an open license (Apache 2.0), along with inference code that accommodates longer contexts available on Hugging Face. This model's weights can seamlessly replace LLaMA in existing systems designed for shorter contexts, specifically those handling up to 2048 tokens. Furthermore, we include evaluation results along with comparisons to the original OpenLLaMA models, thereby providing a comprehensive overview of LongLLaMA's capabilities in the realm of long-context processing.

Gemma represents a collection of cutting-edge, lightweight open models that are built upon the same research and technology underlying the Gemini models. Created by Google DeepMind alongside various teams at Google, the inspiration for Gemma comes from the Latin word "gemma," which translates to "precious stone." In addition to providing our model weights, we are also offering tools aimed at promoting developer creativity, encouraging collaboration, and ensuring the ethical application of Gemma models. Sharing key technical and infrastructural elements with Gemini, which stands as our most advanced AI model currently accessible, Gemma 2B and 7B excel in performance within their weight categories when compared to other open models. Furthermore, these models can conveniently operate on a developer's laptop or desktop, demonstrating their versatility. Impressively, Gemma not only outperforms significantly larger models on crucial benchmarks but also maintains our strict criteria for delivering safe and responsible outputs, making it a valuable asset for developers.

DeepSeek-V3.2-Speciale is the most advanced reasoning-focused version of the DeepSeek-V3.2 family, designed to excel in mathematical, algorithmic, and logic-intensive tasks. It incorporates DeepSeek Sparse Attention (DSA), an efficient attention mechanism tailored for very long contexts, enabling scalable reasoning with minimal compute costs. The model undergoes a robust reinforcement learning pipeline that scales post-training compute to frontier levels, enabling performance that exceeds GPT-5 on internal evaluations. Its achievements include gold-medal-level solutions in IMO 2025, IOI 2025, ICPC World Finals, and CMO 2025, with final submissions publicly released for verification. Unlike the standard V3.2 model, the Speciale variant removes tool-calling capabilities to maximize focused reasoning output without external interactions. DeepSeek-V3.2-Speciale uses a revised chat template with explicit thinking blocks and system-level reasoning formatting. The repository includes encoding tools showing how to convert OpenAI-style chat messages into DeepSeek’s specialized input format. With its MIT license and 685B-parameter architecture, DeepSeek-V3.2-Speciale offers cutting-edge performance for academic research, competitive programming, and enterprise-level reasoning applications.

Grok 4 Heavy represents xAI’s flagship AI model, leveraging a multi-agent architecture to deliver exceptional reasoning, problem-solving, and multimodal understanding. Developed using the Colossus supercomputer, it achieves a remarkable 50% score on the HLE benchmark, placing it among the leading AI models worldwide. This version can process text, images, and is expected to soon support video inputs, enabling richer contextual comprehension. Grok 4 Heavy is designed for advanced users, including developers and researchers, who demand state-of-the-art AI capabilities for complex scientific and technical tasks. Available exclusively through a $300/month SuperGrok Heavy subscription, it offers early access to future innovations like video generation. xAI has addressed past controversies by strengthening content moderation and removing harmful prompts. The platform aims to push AI boundaries while balancing ethical considerations. Grok 4 Heavy is positioned as a formidable competitor to other leading AI systems.

DeepSeek R2 is the highly awaited successor to DeepSeek R1, an innovative AI reasoning model that made waves when it was introduced in January 2025 by the Chinese startup DeepSeek. This new version builds on the remarkable achievements of R1, which significantly altered the AI landscape by providing cost-effective performance comparable to leading models like OpenAI’s o1. R2 is set to offer a substantial upgrade in capabilities, promising impressive speed and reasoning abilities akin to that of a human, particularly in challenging areas such as complex coding and advanced mathematics. By utilizing DeepSeek’s cutting-edge Mixture-of-Experts architecture along with optimized training techniques, R2 is designed to surpass the performance of its predecessor while keeping computational demands low. Additionally, there are expectations that this model may broaden its reasoning skills to accommodate languages beyond just English, potentially increasing its global usability. The anticipation surrounding R2 highlights the ongoing evolution of AI technology and its implications for various industries.

Llama 4 Maverick is a cutting-edge multimodal AI model with 17 billion active parameters and 128 experts, setting a new standard for efficiency and performance. It excels in diverse domains, outperforming other models such as GPT-4o and Gemini 2.0 Flash in coding, reasoning, and image-related tasks. Llama 4 Maverick integrates both text and image processing seamlessly, offering enhanced capabilities for complex tasks such as visual question answering, content generation, and problem-solving. The model’s performance-to-cost ratio makes it an ideal choice for businesses looking to integrate powerful AI into their operations without the hefty resource demands.