MiniMax M2.1 arrives with a focus on real-world, multi-language development
MiniMax has released MiniMax M2.1, an update aimed at improving performance on complex, real-world programming tasks and office automation workflows. The model is available on the MiniMax Open Platform and as open model weights on Hugging Face: https://platform.minimax.io/docs/guides/text-generation and https://huggingface.co/MiniMaxAI/MiniMax-M2.1. The original announcement is here: https://www.minimax.io/news/minimax-m21
What’s new in M2.1
MiniMax positions M2.1 as an iteration that shifts priorities from accessibility and cost (the focus of M2) toward stronger usability across multiple programming languages and office scenarios. Key technical emphases include:
- Expanded multilingual coding capabilities across Rust, Java, Golang, C++, Kotlin, Objective-C, TypeScript, JavaScript, and others — covering tasks from low-level system work to application-layer development.
- Stronger WebDev and AppDev support, with explicit improvements for native Android and iOS development and better design and aesthetic understanding for web and app interfaces.
- Composite instruction constraints and Interleaved Thinking, boosting systematic problem solving and enabling the model to better follow multi-step, constraint-heavy instructions common in office workflows.
- Concise responses and reduced token use, reported to improve response speed and efficiency for coding and agent-driven continuous workflows.
- Improved agent/tool scaffolding generalization, with consistent behavior across multiple tool chains and context-management schemes.
Benchmarks and the VIBE suite
M2.1 is reported to deliver noticeable gains over M2 on software engineering leaderboards, particularly in multilingual scenarios where it is said to outperform Claude Sonnet 4.5 and approach Claude Opus 4.5 on some measures. The team introduced a new full-stack benchmark, VIBE (Visual & Interactive Benchmark for Execution), which evaluates Web, Simulation, Android, iOS, and Backend development using an Agent-as-a-Verifier (AaaV) approach to test interactive logic and visual aesthetics in runtime.
- VIBE aggregate score: 88.6
- VIBE-Web: 91.5
- VIBE-Android: 89.7
Additional reported improvements include test-case generation, code performance optimization, code review, instruction following, and long-horizon tool use.
Agentic capabilities and office automation
M2.1 expands the concept of a “Digital Employee.” The model can accept web content in text form and drive mouse and keyboard actions via text-based commands, enabling end-to-end automations across administration, data science, finance, HR, and software development. Demonstrated demos include administrative equipment procurement workflows, project-management triage and status updates, and searching merge requests to identify relevant changes.
Tool and agent integrations listed in the announcement include support for Claude Code, Droid (Factory AI), Cline, Kilo Code, Roo Code, BlackBox, and context-management formats such as Skill.md, Claude.md/agent.md/cursorrule, and Slash Commands.
Showcases
The release highlights a variety of practical demos across stacks and formats, illustrating the model’s full-stack capabilities:
- 3D interactive animations using React Three Fiber (example: a 3D Christmas tree rendering thousands of instances) — try hosted demo: https://yuyl27wq92.space.minimax.io/
- Avant-garde and brand-oriented web UIs — try demos: https://m6xkaf07udss.space.minimax.io/ and https://2drpfocv00n9.space.minimax.io/
- Web 3D Lego sandbox using Three.js — https://8e6nunemyuzh.space.minimax.io/
- Web Audio drum machine built on the Web Audio API — https://21okxwno2u.space.minimax.io
- Rust TUI security-audit tool, Python Web3 dashboard, C++/GLSL real-time rendering, Java real-time Danmaku, and interactive SVG generation — https://08tmc3aada59.space.minimax.io/
Local deployment and recommended inference stacks
Model weights are open-source on Hugging Face: https://huggingface.co/MiniMaxAI/MiniMax-M2.1
Recommended inference frameworks and guides:
- SGLang — deployment guide: https://huggingface.co/MiniMaxAI/MiniMax-M2.1/blob/main/docs/sglang_deploy_guide.md
- vLLM — deployment guide: https://huggingface.co/MiniMaxAI/MiniMax-M2.1/blob/main/docs/vllm_deploy_guide.md and project: https://github.com/vllm-project/vllm
- Transformers — deployment guide: https://github.com/MiniMax-AI/MiniMax-M2.1/blob/main/docs/transformers_deploy_guide.md and repo: https://github.com/huggingface/transformers
- Ktransformers tutorial: https://github.com/kvcache-ai/ktransformers/blob/main/doc/en/kt-kernel/MiniMax-M2.1-Tutorial.md
Recommended inference parameters: temperature=1.0, top_p=0.95, top_k=40. Tool-calling instructions are available at: https://huggingface.co/MiniMaxAI/MiniMax-M2.1/blob/main/docs/tool_calling_guide.md
How to access
- MiniMax Open Platform API and docs: https://platform.minimax.io/docs/guides/text-generation
- MiniMax Agent product: https://agent.minimax.io/
- Model weights and deployment docs: https://huggingface.co/MiniMaxAI/MiniMax-M2.1
Original announcement: https://www.minimax.io/news/minimax-m21