Minimax M2.5
Parameters
-
Context Length
128K
Modality
Multimodal
Architecture
Dense
License
Proprietary
Release Date
15 Dec 2025
Knowledge Cutoff
-
Technical Specifications
Attention Structure
Multi-Head Attention
Hidden Dimension Size
-
Number of Layers
-
Attention Heads
-
Key-Value Heads
-
Activation Function
-
Normalization
-
Position Embedding
Absolute Position Embedding
Minimax M2.5
Minimax M2.5 is an advanced multimodal model offering state-of-the-art text generation and reasoning capabilities. Features strong multilingual support with particular emphasis on Chinese and English. Designed for versatile applications including content generation, analysis, and conversational AI with competitive performance across multiple benchmarks.
About Minimax M2
Minimax M2.5 series represents cutting-edge multimodal AI models from Minimax AI, featuring state-of-the-art performance in text generation, reasoning, and multilingual understanding. These models combine high-quality language understanding with efficient architecture, optimized for both API deployment and enterprise solutions.
Other Minimax M2 Models
- No related models available
Evaluation Benchmarks
Rank
#47
| Benchmark | Score | Rank |
|---|---|---|
Web Development WebDev Arena | 1422 | 14 |
StackUnseen ProLLM Stack Unseen | 0.66 | 15 |
Agentic Coding LiveBench Agentic | 0.52 | 16 |
Graduate-Level QA GPQA | 0.81 | 20 |
Mathematics LiveBench Mathematics | 0.77 | 23 |
Reasoning LiveBench Reasoning | 0.59 | 30 |
Professional Knowledge MMLU Pro | 0.80 | 30 |
Coding LiveBench Coding | 0.71 | 32 |
Data Analysis LiveBench Data Analysis | 0.50 | 35 |
Rankings
Overall Rank
#47
Coding Rank
#37