HomeMiniMax-M2
230B
Model parameter quantity
MiniMax
Affiliated organization
Open Source
License Type
October 25, 2025
Release time
Model Introduction
The latest flagship model released by Minimax features excellent general capabilities, advanced programming capabilities, powerful agent performance, and efficient architecture design.
Comprehensive score
Language dialogue
Knowledge reserve
Reasoning association
Mathematical calculation
Code writing
Command following
Swipe left and right to view more
Language comprehension ability
Capable of understanding complex contexts and generating logically coherent sentences, though occasionally off in tone control.
7.6
Knowledge coverage scope
Possesses core knowledge of mainstream disciplines, but has limited coverage of cutting-edge interdisciplinary fields.
8.3
Reasoning ability
Unable to maintain coherent reasoning chains, often causing inverted causality or miscalculations.
5.5
Model comparison
MiniMax-M2 vs Doubao-Seed-1.6-251015 (Thinking)
The deep reasoning model released by ByteDance, which supports manual switching of deep reasoning, and its performance is significantly improved compared to doubao-1.5.
MiniMax-M2 vs Doubao-Seed-1.6-thinking-250715
The latest version of the seed series model launched by ByteDance, which supports the thinking mode.
Related model
MiniMax-M2.7
MiniMax-M2.7 is MiniMax’s new-generation general-purpose large model. By building an Agent Harness system, it deeply participates in its own training and optimization process, can take on 30%–50% of the workload in some R&D scenarios, and achieves about a 30% improvement on internal evaluation benchmarks.
MiniMax-M2.1
The latest flagship model released by Minimax features excellent general capabilities, advanced programming capabilities, powerful agent performance, and efficient architecture design.
MiniMax-Text-01
MiniMax-Text-01 is a powerful language model with 456 billion total parameters, of which 45.9 billion are activated per token. To better unlock the long context capabilities of the model, MiniMax-Text-01 adopts a hybrid architecture that combines Lightning Attention, Softmax Attention and Mixture-of-Experts (MoE).
MiniMax-M1-80k
The world's first open-weight, large-scale hybrid-attention reasoning model released by Minimax
abab6.5
abab6.5 is an API model produced by MiniMax, with the version number being abab6.5. The abab6.5 serie is a trillion-parameter Mixture of Experts (MoE) large language model. The abab6.5 is suitable for complex scenarios, such as application problem calculations, scientific computations, and other similar scenarios. The abab6.5s is suitable for general scenarios.
Relevant documents
Former OpenAI Chief Scientist Ilya’s SSI Unveils First Model
AI has achieved another major milestone. Following his departure from OpenAI, former chief scientist Ilya Sutskever established Safe Superintelligence Inc. (SSI), which has recently unveiled details regarding its inaugural model. Reports from oversea
Lovable Leads Atech's Seed Round as AI Ambient Coding Officially Enters the Hardware Field
On May 14, 2026, AI application development platform Lovable announced its participation in the $800,000 seed funding round for Danish hardware startup Atech. Led by Lovable, the round attracted top-tier venture capital firms including the a16z Scout
Anthropic Expands Claude AI Coding Tools to Japan in Push for Overseas Growth
Anthropic, a prominent U.S. artificial intelligence firm, is intensifying its global outreach. On Wednesday, the company hosted a major developer gathering, "Code with Claude," in Tokyo, drawing close to 500 software engineers. This initiative seeks
India’s Software Giant Cuts Hiring, Promises No Layoffs as AI Agents Scale Up
As artificial intelligence reshapes traditional labor-intensive business models, Tata Consultancy Services (TCS), a premier Indian software outsourcing firm, has unveiled its strategic response. During Tuesday’s annual general meeting, the chairman o
China Locks AI Models During Gaokam to Block Instant Homework Help
With the 2026 Gaokao fast approaching, rumors regarding the suspension of AI tools during the exam period have ignited intense online debate. In response to public concern, major AI platforms and educational apps have clarified their stance: rather t
