Inkling
Inkling is an open-weights multimodal AI model from Thinking Machines designed as a customizable foundation model for developers, researchers, and enterprises. The model is a Mixture-of-Experts transformer with 975 billion total parameters, 41 billion active parameters, and support for context windows up to 1 million tokens. Inkling was trained from scratch on text, images, audio, and video, giving it native capabilities across reasoning, coding, agentic tool use, vision, audio, factuality, and instruction following. It is built with controllable thinking effort so users can balance performance, latency, and token efficiency for different workloads. The model is available for fine-tuning on Tinker, with playground access, API availability through ecosystem partners, and full weights published on Hugging Face. Built for customization, Inkling gives teams an open-weights base model for building domain-specific AI systems, multimodal agents, coding workflows, research tools, and more.
Learn more about Inkling
MiMo-V2.6-Pro
5.0 out of 5 stars
(1 Rating)
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.
Learn more about MiMo-V2.6-Pro
Laguna S 2.1
5.0 out of 5 stars
(1 Rating)
Laguna S 2.1 is an open weight agentic coding model designed to pursue longer-horizon work and make effective use of reasoning. It uses a 118-billion-parameter Mixture-of-Experts architecture with 8 billion active parameters per token and supports a context window of up to one million tokens in both thinking and no-thinking modes. Its compact active size makes it suitable for complex work on local machines while remaining competitive with models many times larger on terminal, software-engineering, codebase-question-answering, and tool-use benchmarks. Laguna S 2.1 is built to keep working through difficult tasks with greater persistence, verification, and willingness to backtrack instead of declaring success too early. In demonstrated runs, it built and validated a browser rendering engine from an empty folder, optimized an agent harness for faster execution and substantially lower memory allocation, and completed extended mathematical research using the tools in its environment.
Learn more about Laguna S 2.1
SWE-2
5.0 out of 5 stars
(1 Rating)
SWE-2 is Cognition’s advanced coding model designed to improve software engineering performance while reducing the cost of agentic coding workflows. The model is post-trained from Kimi K3 and uses reinforcement learning to optimize multiple reasoning-effort levels within a single training run. SWE-2 is designed to explore codebases more selectively, begin implementation sooner, and complete tasks with fewer redundant reads and reasoning steps than earlier Cognition models. Its capabilities include code generation, debugging, test creation, verification, repository analysis, and complex terminal-based software engineering tasks. The model also emphasizes stronger engineering judgment, end-to-end test coverage, instruction following, and evidence-based verification of user assumptions. SWE-2 is available through Devin Desktop and Devin CLI, with broader rollout planned across Devin Web and Fusion.
Learn more about SWE-2