MiniMax M2.5
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams.
Input
Output
Context
197K
Max Output
197K
Parameters
—
Technical Specifications
Model TypeChat
Context Window197K
Max Output Tokens197K
Parameters—
Training Cutoff—
License—
Capabilities
Input Modalities
text
Output Modalities
text
Features
code_generationreasoning
Benchmarks
19.1%
HLE
84.8%
GPQA
42.6%
SciCode
37.4
Coding
41.9
Intelligence
108
Speed (tok/s)
19.8
TTFA (s)
1.2
TTFT (s)
Resources & Links
Related Tools
Data sourced from official provider APIs and documentation
Last updated: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.