Best AI Reasoning Models for Hugging Face
View:
Compare the Top AI Reasoning Models that integrate with Hugging Face as of October 2026
Sort By:
This a list of AI Reasoning Models that integrate with Hugging Face. Use the filters on the left to add additional filters for products that have integrations with Hugging Face. View the products that work with Hugging Face in the table below.
What are AI Reasoning Models for Hugging Face?
AI reasoning models are artificial intelligence models designed to perform complex problem-solving, logical reasoning, planning, and multi-step decision-making beyond traditional language generation. These models use advanced inference techniques to break down difficult tasks, evaluate alternatives, apply logic, and generate more accurate responses for domains such as mathematics, programming, scientific research, business analysis, and autonomous AI agents. AI reasoning models often support extended context windows, tool use, code execution, structured outputs, and agentic workflows to solve complex real-world problems. Many are available through APIs, cloud platforms, and AI development frameworks, enabling developers to build intelligent applications and autonomous systems. By combining language understanding with advanced reasoning capabilities, AI reasoning models help organizations improve decision-making, automate complex workflows, and power next-generation AI applications. Compare and read user reviews of the best AI Reasoning Models for Hugging Face currently available using the table below. This list is updated regularly.
-
1
MiMo-V2.6-Flash
Xiaomi Technology
MiMo-V2.6-Flash is an open-source, natively omnimodal AI model from Xiaomi MiMo designed to balance intelligence, efficiency, and cost. The model supports coding, general agent workflows, visual reasoning, computer use, automation, and multimodal creative tasks. Its capabilities extend beyond software engineering into frontend design, presentation creation, 3D modeling, interactive world generation, video production, and embodied simulation. Xiaomi trained MiMo-V2.6-Flash with large-scale reinforcement learning across coding, general agent, visual, and cybersecurity tasks, completing roughly 750,000 training trajectories. The model is positioned as the more cost-efficient member of the MiMo-V2.6 family while retaining strong performance across software engineering, tool use, automation, and visual coding benchmarks. MiMo-V2.6-Flash is available through MiMo Desktop, AI Studio, MiMo Code, the Xiaomi MiMo API Platform, OpenRouter, and the open-source MiMo-V2.6 release.Starting Price: Free -
2
MiMo-V2.6-Pro
Xiaomi Technology
MiMo-V2.6-Pro is Xiaomi MiMo’s most capable open-source omnimodal AI model, built for coding, general agent workflows, visual tasks, research, and multimodal creation. The model combines strong software engineering capabilities with computer use, 3D spatial reasoning, visual perception, and tool use for complex multi-step work. MiMo-V2.6-Pro can build interactive 3D environments, generate Blender models, create frontend interfaces and presentations, and coordinate agents to refine outputs through visual feedback. It also supports research workflows such as literature review, computational experimentation, materials discovery, and formal mathematical proof development. Xiaomi trained the model with large-scale reinforcement learning across coding, general agents, visual tasks, and cybersecurity environments and has open-sourced the technical report, training environments, and RL code.Starting Price: Free -
3
Qwen3.8-Max
Alibaba
Qwen3.8-Max is Qwen’s most capable model to date, built as a Max-class AI model for coding, work, research, long-horizon tasks, and multimodal agents. It scales to 2.4 trillion parameters with 95 billion active parameters and is available through QwenCloud. The model is designed to complete complex, open-ended tasks end to end with greater reliability and minimal human involvement. Qwen3.8-Max supports autonomous coding workflows, agentic development, research reproduction, visual reasoning, document understanding, video analysis, and real-world productivity tasks. It can integrate with popular agent frameworks and coding assistants, including Claude Code, Codex, Qoder CLI, Qwen Code, and OpenClaw. Built for developers, researchers, enterprises, and AI agent builders, Qwen3.8-Max helps teams automate sophisticated work across code, documents, tools, interfaces, and multimodal content.Starting Price: $2 per 1M (input) -
4
Muse Glimmer
Meta
Muse Glimmer is a 30-billion-parameter open-weights model from Meta Superintelligence Labs, optimized for always-on local agent workflows. Small enough to run on a Mac or PC with a single consumer GPU, it is designed for local agents, function calling, coding, and LLM-as-a-judge evaluation without depending on cloud infrastructure or network access. The model combines long-horizon execution, precise tool calling, multimodal understanding, long-context memory, and instruction following. It can complete end-to-end agentic tasks, sustain multi-step reasoning across extended workflows, recover from failed or unexpected tool calls, and accept interleaved text and images through a dedicated perception encoder for interpreting screenshots, charts, and documents. Muse Glimmer works with OpenClaw and other agentic orchestration patterns, supports controllable reasoning effort, and is trained on data from more than 100 languages.Starting Price: Free -
5
Qwen3.8-27B
Alibaba
Qwen3.8-27B is a compact open-weights model in Alibaba’s Qwen3.8 family, aimed at developers and researchers who want strong local AI performance without using the full Max-scale model. Reports from Alibaba’s Qwen3.8 launch state that Qwen3.8-27B was planned for open-weight release alongside Qwen3.8-Max, expanding access for builders working on AI applications. The model is positioned for coding, research, professional workflows, and local deployment scenarios where a 27B model can be more practical than frontier-scale systems. Qwen3.8’s broader launch emphasizes software development, document processing, data analysis, and professional “cowork” use cases. Qwen3.8-27B is especially relevant for teams that need a capable open model for experimentation, coding agents, assistant workflows, and self-hosted inference. Built for practical deployment, Qwen3.8-27B gives developers a smaller Qwen3.8 option for building AI tools, testing agents, and running advanced language model workflows. -
6
Kimi K2 Thinking
Moonshot AI
Kimi K2 Thinking is an advanced open source reasoning model developed by Moonshot AI, designed specifically for long-horizon, multi-step workflows where the system interleaves chain-of-thought processes with tool invocation across hundreds of sequential tasks. The model uses a mixture-of-experts architecture with a total of 1 trillion parameters, yet only about 32 billion parameters are activated per inference pass, optimizing efficiency while maintaining vast capacity. It supports a context window of up to 256,000 tokens, enabling the handling of extremely long inputs and reasoning chains without losing coherence. Native INT4 quantization is built in, which reduces inference latency and memory usage without performance degradation. Kimi K2 Thinking is explicitly built for agentic workflows; it can autonomously call external tools, manage sequential logic steps (up to and typically between 200-300 tool calls in a single chain), and maintain consistent reasoning.Starting Price: Free -
7
Qwen3.6-Max-Preview
Alibaba
Qwen3.6-Max-Preview is a next-generation frontier language model designed to push the limits of intelligence, instruction following, and real-world agent capabilities within the Qwen ecosystem. Building on the Qwen3 series, this preview release introduces stronger world knowledge, sharper instruction alignment, and significant improvements in agentic coding performance, enabling the model to better handle complex, multi-step tasks and software engineering workflows. It is engineered for advanced reasoning and execution scenarios, where the model not only generates responses but also interacts with tools, processes long contexts, and supports structured problem-solving across domains such as coding, research, and enterprise workflows. The architecture continues the Qwen focus on large-scale, high-efficiency models capable of handling extensive context windows and delivering consistent performance across multilingual and knowledge-intensive tasks.Starting Price: Free -
8
Qwen3
Alibaba
Qwen3, the latest iteration of the Qwen family of large language models, introduces groundbreaking features that enhance performance across coding, math, and general capabilities. With models like the Qwen3-235B-A22B and Qwen3-30B-A3B, Qwen3 achieves impressive results compared to top-tier models, thanks to its hybrid thinking modes that allow users to control the balance between deep reasoning and quick responses. The platform supports 119 languages and dialects, making it an ideal choice for global applications. Its pre-training process, which uses 36 trillion tokens, enables robust performance, and advanced reinforcement learning (RL) techniques continue to refine its capabilities. Available on platforms like Hugging Face and ModelScope, Qwen3 offers a powerful tool for developers and researchers working in diverse fields.Starting Price: Free -
9
DeepSeek V3.1
DeepSeek
DeepSeek V3.1 is a groundbreaking open-weight large language model featuring a massive 685-billion parameters and an extended 128,000‑token context window, enabling it to process documents equivalent to 400-page books in a single prompt. It delivers integrated capabilities for chat, reasoning, and code generation within a unified hybrid architecture, seamlessly blending these functions into one coherent model. V3.1 supports a variety of tensor formats to give developers flexibility in optimizing performance across different hardware. Early benchmark results show robust performance, including a 71.6% score on the Aider coding benchmark, putting it on par with or ahead of systems like Claude Opus 4 and doing so at a far lower cost. Made available under an open source license on Hugging Face with minimal fanfare, DeepSeek V3.1 is poised to reshape access to high-performance AI, challenging traditional proprietary models.Starting Price: Free -
10
DeepSeek-V3.2-Exp
DeepSeek
Introducing DeepSeek-V3.2-Exp, our latest experimental model built on V3.1-Terminus, debuting DeepSeek Sparse Attention (DSA) for faster and more efficient inference and training on long contexts. DSA enables fine-grained sparse attention with minimal loss in output quality, boosting performance for long-context tasks while reducing compute costs. Benchmarks indicate that V3.2-Exp performs on par with V3.1-Terminus despite these efficiency gains. The model is now live across app, web, and API. Alongside this, the DeepSeek API prices have been cut by over 50% immediately to make access more affordable. For a transitional period, users can still access V3.1-Terminus via a temporary API endpoint until October 15, 2025. DeepSeek welcomes feedback on DSA via its feedback portal. In conjunction with the release, DeepSeek-V3.2-Exp has been open-sourced: the model weights and supporting technology (including key GPU kernels in TileLang and CUDA) are available on Hugging Face.Starting Price: Free -
11
DeepSeek-V3.2
DeepSeek
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.Starting Price: Free -
12
DeepSeek-V3.2-Speciale
DeepSeek
DeepSeek-V3.2-Speciale is a high-compute variant of the DeepSeek-V3.2 model, created specifically for deep reasoning and advanced problem-solving tasks. It builds on DeepSeek Sparse Attention (DSA), a custom long-context attention mechanism that reduces computational overhead while preserving high performance. Through a large-scale reinforcement learning framework and extensive post-training compute, the Speciale variant surpasses GPT-5 on reasoning benchmarks and matches the capabilities of Gemini-3.0-Pro. The model achieved gold-medal performance in the International Mathematical Olympiad (IMO) 2025 and International Olympiad in Informatics (IOI) 2025. DeepSeek-V3.2-Speciale does not support tool-calling, making it purely optimized for uninterrupted reasoning and analytical accuracy. Released under the MIT license, it provides researchers and developers an open, state-of-the-art model focused entirely on high-precision reasoning.Starting Price: Free -
13
Qwen3.6-35B-A3B
Alibaba
Qwen3.5-35B-A3B is part of the Qwen3.5 “Medium” model series, designed as a highly efficient, multimodal foundation model that balances strong reasoning ability with practical deployment requirements. It uses a Mixture-of-Experts (MoE) architecture with 35 billion total parameters but activates only about 3 billion per token, allowing it to deliver performance comparable to much larger models while significantly reducing computational cost. The model integrates a hybrid attention mechanism that combines linear attention with standard attention layers, enabling efficient long-context processing and improved scalability for complex tasks. As a native vision-language model, it can process both text and visual inputs, supporting use cases such as multimodal reasoning, coding, and agent-based workflows. It is designed to function as a general-purpose “AI agent,” capable of planning, tool use, and structured problem solving rather than just conversational responses.Starting Price: Free -
14
MiMo-V2.6-Pro-UltraSpeed
Xiaomi Technology
MiMo-V2.6-Pro-UltraSpeed is a high-speed serving mode for Xiaomi MiMo’s flagship MiMo-V2.6-Pro model, designed for latency-sensitive AI workloads. It delivers the same underlying model quality as MiMo-V2.6-Pro while providing output speeds of up to 20 times faster. The model supports coding, agentic automation, multimodal reasoning, visual design, research, and other complex tool-using workflows. Its capabilities include software engineering, frontend creation, presentation design, 3D modeling, interactive world generation, computer use, and multimodal analysis. MiMo-V2.6-Pro-UltraSpeed is intended for real-time applications where the capabilities of MiMo-V2.6-Pro are needed with substantially faster generation. It is available through MiMo Desktop and the Xiaomi MiMo API Platform.Starting Price: $4.35 per 1 million tokens inp -
15
MiniMax M1
MiniMax
MiniMax‑M1 is a large‑scale hybrid‑attention reasoning model released by MiniMax AI under the Apache 2.0 license. It supports an unprecedented 1 million‑token context window and up to 80,000-token outputs, enabling extended reasoning across long documents. Trained using large‑scale reinforcement learning with a novel CISPO algorithm, MiniMax‑M1 completed full training on 512 H800 GPUs in about three weeks. It achieves state‑of‑the‑art performance on benchmarks in mathematics, coding, software engineering, tool usage, and long‑context understanding, matching or outperforming leading models. Two model variants are available (40K and 80K thinking budgets), with weights and deployment scripts provided via GitHub and Hugging Face. -
16
Qwen3.6
Alibaba
Qwen3.6 is a large language model developed by Alibaba as part of its Qwen AI model family, designed for real-world applications and advanced reasoning tasks. It focuses on improving stability, usability, and performance compared to earlier versions. The model supports multimodal capabilities, allowing it to process and reason across text, images, and other data types. Qwen3.6 is particularly strong in coding and developer workflows, offering improved accuracy for complex programming tasks. It uses a mixture-of-experts architecture, enabling efficient performance while maintaining large-scale model capabilities. The model is designed to be deployable in production environments, including enterprise and cloud-based systems. It can be integrated into applications or run locally using open-weight variants. Overall, Qwen3.6 delivers a powerful, efficient, and versatile AI solution for modern use cases.Starting Price: Free -
17
Qwen3.8-Flash-Next
Alibaba
Qwen3.8-Flash-Next is an open-weight multimodal Mixture-of-Experts model and an early preview of the architecture planned for Qwen4. It systematically upgrades attention, residual connections, embeddings, and optimization to improve capability, computational efficiency, model capacity, and training stability. Its hybrid architecture combines Gated DeltaNet, which efficiently compresses historical information, with Qwen Sparse Attention, which selects important context at the micro-block level to reduce attention and indexing costs on long sequences. Gated Residual widens the residual stream into four branches and dynamically controls information flow across layers, while N-gram Embedding adds large-scale local-pattern memory with very little extra per-token computation and can be offloaded to host memory. The model uses a 125B-parameter main network plus 51B N-gram embedding parameters, while activating only 6B parameters per token.Starting Price: $2 per 1M (input) -
18
Step 5 Preview
StepFun
Step 5 Preview is StepFun’s flagship model for agentic work, designed for real-world tasks across software engineering and professional knowledge work, with particular strength in finance. It natively supports text, image, and video input and provides a 1M-token context window, enabling tasks that require large amounts of information, tool calls, and continuous progress toward a deliverable. The model can analyze long documents, multiple source materials, and conversation history for cross-document question answering and research organization. For programming and software engineering, it works across multiple languages and can support troubleshooting, code changes, verification, and test creation. Its multi-step agent capabilities let applications provide tools for retrieving information, processing documents, conducting deep research, and producing analytical reports. Multimodal understanding combines images, video, and text for chart analysis, screenshot question answering, etc.Starting Price: $0.04 per input -
19
Phi-4
Microsoft
Phi-4 is a 14B parameter state-of-the-art small language model (SLM) that excels at complex reasoning in areas such as math, in addition to conventional language processing. Phi-4 is the latest member of our Phi family of small language models and demonstrates what’s possible as we continue to probe the boundaries of SLMs. Phi-4 is currently available on Azure AI Foundry under a Microsoft Research License Agreement (MSRLA) and will be available on Hugging Face. Phi-4 outperforms comparable and larger models on math related reasoning due to advancements throughout the processes, including the use of high-quality synthetic datasets, curation of high-quality organic data, and post-training innovations. Phi-4 continues to push the frontier of size vs quality. -
20
Phi-4-reasoning
Microsoft
Phi-4-reasoning is a 14-billion parameter transformer-based language model optimized for complex reasoning tasks, including math, coding, algorithmic problem solving, and planning. Trained via supervised fine-tuning of Phi-4 on carefully curated "teachable" prompts and reasoning demonstrations generated using o3-mini, it generates detailed reasoning chains that effectively leverage inference-time compute. Phi-4-reasoning incorporates outcome-based reinforcement learning to produce longer reasoning traces. It outperforms significantly larger open-weight models such as DeepSeek-R1-Distill-Llama-70B and approaches the performance levels of the full DeepSeek-R1 model across a wide range of reasoning tasks. Phi-4-reasoning is designed for environments with constrained computing or latency. Fine-tuned with synthetic data generated by DeepSeek-R1, it provides high-quality, step-by-step problem solving. -
21
Phi-4-reasoning-plus
Microsoft
Phi-4-reasoning-plus is a 14-billion parameter open-weight reasoning model that builds upon Phi-4-reasoning capabilities. It is further trained with reinforcement learning to utilize more inference-time compute, using 1.5x more tokens than Phi-4-reasoning, to deliver higher accuracy. Despite its significantly smaller size, Phi-4-reasoning-plus achieves better performance than OpenAI o1-mini and DeepSeek-R1 at most benchmarks, including mathematical reasoning and Ph.D. level science questions. It surpasses the full DeepSeek-R1 model (with 671 billion parameters) on the AIME 2025 test, the 2025 qualifier for the USA Math Olympiad. Phi-4-reasoning-plus is available on Azure AI Foundry and HuggingFace. -
22
Phi-4-mini-reasoning
Microsoft
Phi-4-mini-reasoning is a 3.8-billion parameter transformer-based language model optimized for mathematical reasoning and step-by-step problem solving in environments with constrained computing or latency. Fine-tuned with synthetic data generated by the DeepSeek-R1 model, it balances efficiency with advanced reasoning ability. Trained on over one million diverse math problems spanning multiple levels of difficulty from middle school to Ph.D. level, Phi-4-mini-reasoning outperforms its base model on long sentence generation across various evaluations and surpasses larger models like OpenThinker-7B, Llama-3.2-3B-instruct, and DeepSeek-R1. It features a 128K-token context window and supports function calling, enabling integration with external tools and APIs. Phi-4-mini-reasoning can be quantized using Microsoft Olive or Apple MLX Framework for deployment on edge devices such as IoT, laptops, and mobile devices. -
23
Phi-4-mini-flash-reasoning
Microsoft
Phi-4-mini-flash-reasoning is a 3.8 billion‑parameter open model in Microsoft’s Phi family, purpose‑built for edge, mobile, and other resource‑constrained environments where compute, memory, and latency are tightly limited. It introduces the SambaY decoder‑hybrid‑decoder architecture with Gated Memory Units (GMUs) interleaved alongside Mamba state‑space and sliding‑window attention layers, delivering up to 10× higher throughput and a 2–3× reduction in latency compared to its predecessor without sacrificing advanced math and logic reasoning performance. Supporting a 64 K‑token context length and fine‑tuned on high‑quality synthetic data, it excels at long‑context retrieval, reasoning tasks, and real‑time inference, all deployable on a single GPU. Phi-4-mini-flash-reasoning is available today via Azure AI Foundry, NVIDIA API Catalog, and Hugging Face, enabling developers to build fast, scalable, logic‑intensive applications. -
24
Command A Reasoning
Cohere AI
Command A Reasoning is Cohere’s most advanced enterprise-ready language model, engineered for high-stakes reasoning tasks and seamless integration into AI agent workflows. The model delivers exceptional reasoning performance, efficiency, and controllability, scaling across multi-GPU setups with support for up to 256,000-token context windows, ideal for handling long documents and multi-step agentic tasks. Organizations can fine-tune output precision and latency through a token budget, allowing a single model to flexibly serve both high-accuracy and high-throughput use cases. It powers Cohere’s North platform with leading benchmark performance and excels in multilingual contexts across 23 languages. Designed with enterprise safety in mind, it balances helpfulness with robust safeguards against harmful outputs. A lightweight deployment option allows running the model securely on a single H100 or A100 GPU, simplifying private, scalable use. -
25
Qwen3.8-2.4T-A95B
Alibaba
Qwen3.8-2.4T-A95B is the largest open model in the Qwen3.8 family, bringing Qwen-Max-class capabilities to an open release. Built on the architectural foundation of Qwen3.5, it delivers substantial improvements across coding, professional work, research, and long-horizon agentic tasks, with a focus on carrying complex, multi-step work through to completion more reliably. The causal language model uses a mixture-of-experts architecture with 2.4 trillion total parameters and 95 billion activated parameters, including 512 experts with 10 routed and one shared expert active at a time. It supports a native context length of 262,144 tokens that can be extended to approximately 1.01 million tokens. Agent execution is strengthened through better autonomous planning and improved handling of environment feedback, while broader compatibility with popular agent harnesses and development tools simplifies integration into existing stacks. -
26
Qwen 4
Alibaba
Qwen 4 is Alibaba’s next-generation Qwen foundation model, announced on September 22, 2026, and currently in training. It will follow the Qwen3.8 generation as part of Alibaba’s broader roadmap for increasingly capable foundation and agentic AI models. Alibaba has not yet published Qwen 4’s parameter count, architecture, benchmark results, context window, pricing, release date, or availability details. The announcement places Qwen 4 within a research strategy focused on large-scale model training, agentic reinforcement learning, multimodal intelligence, and recursive self-improvement. Alibaba separately said that later Qwen 4.5 and Qwen 5 models are expected to scale into the 5-to-10-trillion-parameter range, but that figure was not attributed specifically to Qwen 4. Because Qwen 4 has not yet been released, detailed performance comparisons and production capabilities remain unconfirmed.
- Previous
- You're on page 1
- Next
