最新发布

Open General Intelligence: MiniMax H3 Is Now Open Source

Today, we are officially open-sourcing MiniMax H3, our next-generation general-purpose video model.

MiniMax H3: An Open Model Breaking the Boundaries Between Tasks and Modalities

Today, we're officially launching MiniMax H3, a general-purpose omni-modal generation model. H3 can jointly understand multimodal contexts spanning text, images, video, and audio. It generates video with native stereo audio at up to 2K resolution and 15 seconds in length.

MiniMax x Shanghai International Film Festival

MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Evolutionary Search

In the M3 release post, we reported the performance of the M3 model on two international mathematical olympiad benchmarks: IMO 2025 and USAMO 2026. With the MaxProof framework, M3 exceeded the human gold-medal threshold on both. This article further elaborates on our technical path toward advancing mathematical proof capabilities, including base model enhancement, verifier alignment, refinement capability building, and the design of the test-time scaling framework MaxProof.

MiniMax M3: Frontier Coding, 1M Context, Native Multimodality — All in One Model

M3 reaches frontier capability on coding and agentic tasks, introduces the brand-new MSA (MiniMax Sparse Attention) supporting up to 1M context, and is a natively multimodal model. It is the only domestic model combining all three Frontier essentials and will be the only open-source one in this class.

MiniMax Agent Team: Built for Long-Running Tasks and Continuous Evolution

Today we are introducing the overall upgrade of MiniMax Agent. We have given the upgraded Agent a new name: Mavis — MiniMax as a Jarvis, your AI butler.

Why Can't the MiniMax LLM Say "Ma Jiaqi"? Internal Investigation of Sparse Token Forgetting

The MiniMax M2 series has attracted widespread attention from the developer community. This article presents our internal investigation into the sparse token forgetting phenomenon.

MiniMax M2.7: Early Echoes of Self-Evolution

M2.7 is MiniMax's first model deeply participating in its own evolution, excelling at software engineering, professional work, and entertainment with native Agent Teams and self-evolving capabilities.

Forge: Scalable Agent RL Framework and Algorithm

Scaling reinforcement learning for real-world agents runs into a three-way conflict: system throughput, training stability, and agent flexibility all pull in different directions, and that tension has

MiniMax M2.5: Built for Real-World Productivity.

MiniMax M2.5: Built for Real-World Productivity.

A Deep Dive into the MiniMax-M2-her

Worlds to Dream, Stories to Live. How we built a Role-Play Agent for the production usage. This year marks our third year optimizing Role-Play in Talkie / Xingye. Three years is long enough for a pro

MiniMax M2.1: Significantly Enhanced Multi-Language Programming, Built for Real-World Complex Tasks

MiniMax M2.1 delivers industry-leading multi-language programming capabilities across Rust, Java, Go, C++, TypeScript and more, with enhanced mobile development, aesthetic web design, concise responses, and robust Agent framework generalization.