Search Results for "reasoning"
Sort By:
Showing 141 open source projects for "reasoning"
View related business solutions-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
1
Kimi K2.5
Moonshot's most powerful AI model
Kimi K2.5 is Moonshot AI’s open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed vision and text tokens. Based on a 1T-parameter Mixture-of-Experts (MoE) architecture with 32B activated parameters, it integrates advanced language reasoning with strong visual understanding. K2.5 supports both “Thinking” and “Instant” modes, enabling either deep step-by-step reasoning or low-latency responses depending on the task. Designed for agentic workflows, it features an Agent Swarm mechanism that decomposes complex problems into coordinated sub-agents executing in parallel. ... -
2
Ring
Ring is a reasoning MoE LLM provided and open-sourced by InclusionAI
Ring is a reasoning Mixture-of-Experts (MoE) large language model (LLM) developed by inclusionAI. It is built from or derived from Ling. Its design emphasizes reasoning, efficiency, and modular expert activation. In its “flash” variant (Ring-flash-2.0), it optimizes inference by activating only a subset of experts. It applies reinforcement learning/reasoning optimization techniques. -
3
DeepSeek R1
Open-source, high-performance AI model with advanced reasoning
DeepSeek-R1 is an open-source large language model developed by DeepSeek, designed to excel in complex reasoning tasks across domains such as mathematics, coding, and language. DeepSeek R1 offers unrestricted access for both commercial and academic use. The model employs a Mixture of Experts (MoE) architecture, comprising 671 billion total parameters with 37 billion active parameters per token, and supports a context length of up to 128,000 tokens. -
4
MiniCPM4.1
Achieving 3+ generation speedup on reasoning tasks
MiniCPM4.1 is an enhanced iteration of the MiniCPM4 architecture, introducing improvements in reasoning capabilities, inference speed, and hybrid operation modes that allow dynamic switching between deep reasoning and standard generation. It builds upon the same efficiency-focused philosophy but further optimizes decoding performance, achieving substantial speed gains in reasoning-intensive tasks while maintaining high-quality outputs. -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
5
GLM-4.6
Agentic, Reasoning, and Coding (ARC) foundation models
GLM-4.6 is the latest iteration of Zhipu AI’s foundation model, delivering significant advancements over GLM-4.5. It introduces an extended 200K token context window, enabling more sophisticated long-context reasoning and agentic workflows. The model achieves superior coding performance, excelling in benchmarks and practical coding assistants such as Claude Code, Cline, Roo Code, and Kilo Code. Its reasoning capabilities have been strengthened, including improved tool usage during inference and more effective integration within agent frameworks. ... -
6
GLM-4.7
Advanced language and coding AI model
...GLM-4.7 also advances “vibe coding,” producing cleaner, more modern UIs, better-structured webpages, and visually improved slide layouts. Its tool-use capabilities are substantially enhanced, with notable improvements in browsing, search, and tool-integrated reasoning tasks. Overall, GLM-4.7 shows broad performance upgrades across coding, reasoning, chat, creative writing, and role-play scenarios. -
7
Step 3.5 Flash
Fast, Sharp & Reliable Agentic Intelligence
...Its design targets deep reasoning, long-context handling, coding, and real-time responsiveness, making it suitable for building autonomous agents, advanced assistants, and long-chain cognitive workflows without sacrificing performance. -
8
OpenMythos
A theoretical reconstruction of the Claude Mythos architecture
...The project explores the idea that instead of stacking hundreds of unique transformer layers, a smaller set of layers can be reused iteratively during inference to achieve deeper reasoning without increasing parameter count. It divides computation into three main stages, including a pre-processing phase, a looped recurrent reasoning block, and a final output refinement stage, creating a structured pipeline for inference. The architecture incorporates advanced techniques such as mixture-of-experts routing, adaptive computation time, and multiple attention mechanisms to dynamically allocate compute where needed. ... -
9
Qwen3-VL
Qwen3-VL, the multimodal large language model series by Alibaba Cloud
Qwen3-VL is the latest multimodal large language model series from Alibaba Cloud’s Qwen team, designed to integrate advanced vision and language understanding. It represents a major upgrade in the Qwen lineup, with stronger text generation, deeper visual reasoning, and expanded multimodal comprehension. The model supports dense and Mixture-of-Experts (MoE) architectures, making it scalable from edge devices to cloud deployments, and is available in both instruction-tuned and reasoning-enhanced variants. Qwen3-VL is built for complex tasks such as GUI automation, multimodal coding (converting images or videos into HTML, CSS, JS, or Draw.io diagrams), long-context reasoning with support up to 1M tokens, and comprehensive video understanding. ... -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
10
Poetiq
Reproduction of Poetiq's record-breaking submission to the ARC-AGI-1
poetiq-arc-agi-solver is the open-source codebase from Poetiq that replicates their record-breaking submission to the challenging benchmark suite ARC-AGI (both ARC-AGI-1 and ARC-AGI-2). The project demonstrates a system that orchestrates large language models (LLMs) — like those from major providers — with carefully engineered prompting, reasoning workflows, and dynamic strategies, to tackle the abstract, logic-heavy problems in ARC-AGI. Instead of relying on a single prompt or fixed strategy, their solver dynamically adapts the reasoning path, selecting what to ask or analyze next depending on intermediate results — effectively compositing reasoning, perception, and program synthesis (or symbolic manipulation) in a loop. ... -
11
GLM-5
From Vibe Coding to Agentic Engineering
GLM-5 is a next-generation open-source large language model (LLM) developed by the Z .ai team under the zai-org organization that pushes the boundaries of reasoning, coding, and long-horizon agentic intelligence. Building on earlier GLM series models, GLM-5 dramatically scales the parameter count (to roughly 744 billion) and expands pre-training data to significantly improve performance on complex tasks such as multi-step reasoning, software engineering workflows, and agent orchestration compared to its predecessors like GLM-4.5. ... -
12
GLM-4.6V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
GLM-4.6V represents the latest generation of the GLM-V family and marks a major step forward in multimodal AI by combining advanced vision-language understanding with native “tool-call” capabilities, long-context reasoning, and strong generalization across domains. Unlike many vision-language models that treat images and text separately or require intermediate conversions, GLM-4.6V allows inputs such as images, screenshots or document pages directly as part of its reasoning pipeline — and can output or act via tools seamlessly, bridging perception and execution. ... -
13
J-Space Cognition Suite V3.6
AI cognitive-enhancement Skills based on Anthropic's J-space
...Core mechanisms include shared workspace anchors, compact reasoning tracks, metacognitive control, explicit intermediate reasoning, and empirical verification. An optional Python controller records goals, checkpoints, open questions, recovery state, and task continuity. -
14
Qwen2.5-Math
A series of math-specific large language models of our Qwen2 series
...It includes base models (1.5B / 7B / 72B parameters), instruction-tuned versions, and a reward model (RM) to improve alignment. Unlike its predecessor Qwen2-Math, Qwen2.5-Math supports both Chain-of-Thought (CoT) reasoning and Tool-Integrated Reasoning (TIR) for solving math problems, and works in both Chinese and English. It is optimized for solving mathematical benchmarks and exams; the 72B-Instruct model achieves state-of-the-art results among open source models on many English and Chinese math tasks. -
15
GLM-4.5V
GLM-4.6V/4.5V/4.1V-Thinking, towards versatile multimodal reasoning
GLM-4.5V is the preceding iteration in the GLM-V series that laid much of the groundwork for general multimodal reasoning and vision-language understanding. It embodies the design philosophy of mixing visual and textual modalities into a unified model capable of general-purpose reasoning, content understanding, and generation, while already supporting a wide variety of tasks: from image captioning and visual question answering to content recognition, GUI-based agents, video understanding, and long-document interpretation. ... -
16
VibeThinker
Diversity-driven optimization and large-model reasoning ability
VibeThinker is a compact but high-capability open-source language model released by WeiboAI (Sina AI Lab). It contains about 1.5 billion parameters, far smaller than many “frontier” models, yet it is explicitly optimized for reasoning, mathematics, and code generation tasks rather than general open-domain chat. The innovation lies in its training methodology: the team uses what they call the Spectrum-to-Signal Principle (SSP), where a first stage emphasizes diversity of reasoning paths (the “spectrum” phase) and a second stage uses reinforcement techniques (the “signal” phase) to refine toward correctness and strong reasoning. -
17
MiniMax-M1
Open-weight, large-scale hybrid-attention reasoning model
MiniMax-M1 is presented as the world’s first open-weight, large-scale hybrid-attention reasoning model, designed to push the frontier of long-context, tool-using, and deeply “thinking” language models. It is built on the MiniMax-Text-01 foundation and keeps the same massive parameter budget, but reworks the attention and training setup for better reasoning and test-time compute scaling. Architecturally, it combines Mixture-of-Experts layers with lightning attention, enabling the model to support a native context length of 1 million tokens while using far fewer FLOPs than comparable reasoning models for very long generations. ... -
18
GLM-4.5
GLM-4.5: Open-source LLM for intelligent agents by Z.ai
...The models support FP8 and BF16 precision, and can handle very large context windows of up to 128K tokens. Flexible inference is supported through frameworks like vLLM and SGLang with tool-call and reasoning parsers included. -
19
GLM-5.1
GLM-5: From Vibe Coding to Agentic Engineering
GLM-5.1 is a next-generation large language model developed by Z.ai for advanced coding, reasoning, and long-horizon agentic engineering tasks. Built as the successor to GLM-5, the model significantly improves performance in software engineering benchmarks, repository generation, and real-world terminal-based workflows. GLM-5.1 is designed to remain effective over extended problem-solving sessions, allowing it to iteratively refine strategies, analyze failures, and sustain productivity across hundreds of reasoning cycles and tool calls. ... -
20
gpt-oss
gpt-oss-120b and gpt-oss-20b are two open-weight language models
gpt-oss is OpenAI’s open-weight family of large language models designed for powerful reasoning, agentic workflows, and versatile developer use cases. The series includes two main models: gpt-oss-120b, a 117-billion parameter model optimized for general-purpose, high-reasoning tasks that can run on a single H100 GPU, and gpt-oss-20b, a lighter 21-billion parameter model ideal for low-latency or specialized applications on smaller hardware. -
21
Kimi K2
Kimi K2 is the large language model series developed by Moonshot AI
...With its high-dimensional attention mechanisms and expert routing, Kimi-K2 excels across benchmarks in live coding, math reasoning, and problem solving. -
22
Bonsai 27B
Run Bonsai (1-bit) and Ternary-Bonsai language models locally
...The models can run on macOS, Linux, and Windows through CPU, Metal, CUDA, Vulkan, ROCm, llama.cpp, or MLX backends. Its 27B models process text, images, screenshots, and PDFs while supporting reasoning and long-context conversations. They also provide OpenAI-compatible tool calling and optional MCP server integration for agentic workflows. Automated setup scripts install dependencies, download models, obtain binaries, and configure interactive interfaces. Users can access the models through command-line prompts, a local chat server, or Open WebUI. -
23
MiMo-V2-Flash
MiMo-V2-Flash: Efficient Reasoning, Coding, and Agentic Foundation
...Architecturally, it highlights attention and prediction choices aimed at accelerating generation while preserving instruction-following quality in complex prompts. The repository typically serves as a launch point for running the model, understanding its intended use cases, and reproducing or extending its evaluation on reasoning and agent-style tasks. In short, MiMo-V2-Flash targets the “high-speed, high-competence” lane for modern LLM applications. -
24
gpt-oss-safeguard
Safety reasoning models built-upon gpt-oss
gpt-oss-safeguard is an open-weight reasoning model family released by OpenAI designed specifically for content safety and moderation tasks. Rather than just outputting a numeric “safety score,” it is trained to reason about content with respect to a user-provided policy, allowing flexible, customizable moderation definitions rather than fixed rules — ideal when different platforms have different safety standards. -
25
DeepSeekMath-V2
Towards self-verifiable mathematical reasoning
DeepSeekMath-V2 is a large-scale open-source AI model designed specifically for advanced mathematical reasoning, theorem proving, and rigorous proof verification. It’s built by DeepSeek as a successor to their earlier math-specialist models. Unlike general-purpose LLMs that might generate plausible-looking math but sometimes hallucinate or mishandle rigorous logic, Math-V2 is engineered to not only generate solutions but also self-verify them, meaning it examines the derivations, checks logical consistency, and flags or corrects mistakes, producing proofs + verification rather than just a final answer. ...