Toggle navigation

Minimax

Available in Shortly AI

MiniMax M2.5

Released February 12, 2026

ReasoningTool Use

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. It is capable of handling the entire development process of various complex systems. It covers full-stack projects across multiple platforms including Web, Android, iOS, Windows, and Mac, encompassing server-side APIs, functional logic, and databases.

Context window
204.8K tokens
Maximum output
131K tokens
Input pricing
$0.30/M
Output pricing
$1.20/M

Independent benchmark

LiveBench historical snapshot

60.1overall

Historical benchmark data from LiveBench, release 2026-01-08. Scores are pinned and are not fetched on page load.

MiniMax M2.5 LiveBench category scores
CategoryScore
Reasoning59.303
Coding70.698
Agentic Coding51.667
Mathematics77.407
Data Analysis49.605
Language55.101
Instruction Following57.233

Benchmarks measure selected evaluation tasks and do not guarantee performance for every prompt or workflow.

FAQ

Similar AI models

Available with one subscription

Start with MiniMax M2.5 in Shortly AI

Keep your conversations, files and model choices together in one workspace.