Provider logo

MiniMax M2.5

minimax/minimax-m2.5
Provider logo

MiniMax M2.5

minimax/minimax-m2.5

MiniMax M2.5 is a productivity-focused flagship model that builds on M2.1 with stronger coding and real-world office workflow performance (Word, Excel, PowerPoint), plus better tool-use planning and token efficiency.

Added Feb 12, 2026

Model weights

Context Window

204.8K

Max Output

131.1K

Input Price (Auto)

$0.31/1M

Output Price (Auto)

$1.26/1M

Cache Read (Auto)

$0.16/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

33.7

Better than 82% of models compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

84.8%

Better than 86% of models compared

HLE

Humanity's Last Exam

19.1%

Better than 82% of models compared

IFBench

Instruction-following benchmark

71.6%

Better than 88% of models compared

T²-Bench Telecom

Conversational AI agents in dual-control scenarios

95.3%

Better than 94% of models compared

AA-LCR

Long context reasoning evaluation

66.0%

Better than 87% of models compared

CritPt

Research-level physics reasoning

1.1%

Coding

SciCode

Python programming for scientific computing

42.6%

Better than 85% of models compared

Terminal-Bench Hard

Agentic coding and terminal use

34.8%

Better than 82% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

26.2%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

88.1%

Last updated Jun 28, 2026

Artificial Analysis

Providers

Choose explicit providers for this model. Auto routing remains available as the default option.

Loading provider options…

Compare MiniMax M2.5 with similar models from the same provider or model family.

MiniMax M3

minimax/minimax-m3

MiniMax M3 is the non-thinking route for MiniMax's open-weights frontier model, built for coding, agent workflows, tool use, and multimodal understanding from step zero. It keeps native thinking disabled for faster direct answers. MiniMax reports 59.0% on SWE-Bench Pro and 66.0% on Terminal Bench 2.1, with Sparse Attention designed to scale context to 1M. It starts with a 512K context cap on NanoGPT for now.

MiniMax M3 Thinking

minimax/minimax-m3:thinking

MiniMax M3 Thinking is the adaptive-thinking version of MiniMax's open-weights frontier model for coding, agent workflows, tool use, long-context tasks, and native multimodal understanding. MiniMax reports 59.0% on SWE-Bench Pro and 66.0% on Terminal Bench 2.1, with Sparse Attention designed to scale context to 1M. It starts with a 512K context cap on NanoGPT for now.

MiniMax Latest

minimax/minimax-latest

Compatibility alias that routes to the newest MiniMax text model. Currently routes to MiniMax M3 (adaptive thinking).

MiniMax M2.7

minimax/minimax-m2.7

MiniMax M2.7 is the first model deeply involved in iterating on its own training. It excels in real-world software engineering (SWE-Pro 56.22%), end-to-end project delivery (VIBE-Pro 55.6%), and complex office workflows with strong tool-use compliance and agentic capabilities.

MiniMax M2.7 Turbo

minimax/minimax-m2.7-turbo

MiniMax M2.7 Turbo is the highspeed and higher priced route for M2.7.

MiniMax M2.1

minimax/minimax-m2.1

MiniMax M2.1 builds on M2 with enhanced context understanding and improved complex tool use. 230B parameter MoE model (10B active) optimized for agentic workflows and long-horizon tasks.