MiniMax M2 offers enhanced reasoning and strong general performance. Optimized for coding and agentic workflows.
Added Jan 12, 2025
Model weightsContext Window
200.0K
Max Output
131.1K
Avg output tokens (7d)
590 tokens
Input Price (Auto)
$0.17/1M
Output Price (Auto)
$1.53/1M
Cache Read (Auto)
$0.085/1M
Capabilities
Benchmarks
Benchmarks
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
28.9
Reasoning
GPQA Diamond
Graduate-level scientific reasoning
77.7%
Better than 66% of models compared
HLE
Humanity's Last Exam
13.7%
Better than 67% of models compared
IFBench
Instruction-following benchmark
72.3%
Better than 89% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
86.8%
Better than 80% of models compared
AA-LCR
Long context reasoning evaluation
65.0%
Better than 69% of models compared
CritPt
Research-level physics reasoning
0.9%
Coding
SciCode
Python programming for scientific computing
36.1%
Better than 56% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
25.8%
Better than 67% of models compared
LiveCodeBench
Contamination-free coding benchmark
82.6%
Better than 94% of models compared
Math
AIME 2025
American Invitational Mathematics Examination 2025
78.3%
Better than 73% of models compared
Knowledge
MMLU-Pro
Professional and academic subject knowledge
82.0%
Better than 78% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
23.2%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
90.9%
Last updated Aug 16, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Related text models
Compare MiniMax M2 with similar models from the same provider or model family.
MiniMax M3
minimax/minimax-m3MiniMax 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:thinkingMiniMax 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-latestCompatibility alias that routes to the newest MiniMax text model. Currently routes to MiniMax M3 (adaptive thinking).
MiniMax M2.7
minimax/minimax-m2.7MiniMax 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-turboMiniMax M2.7 Turbo is the highspeed and higher priced route for M2.7.
MiniMax M2.5
minimax/minimax-m2.5MiniMax 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.