Private AI
MiniMax M2.5 is a productivity-focused flagship model with stronger coding and office workflow performance (Word, Excel, PowerPoint), plus improved tool planning and token efficiency. Running inside a TEE (Trusted Execution Environment), with provider attestation support.
Added Apr 20, 2026
Model weightsContext Window
196.6K
Max Output
131.1K
Input Price (Auto)
$0.20/1M
Output Price (Auto)
$1.38/1M
Cache Read (Auto)
$0.10/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
33.7
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
GPQA Diamond
Graduate-level scientific reasoning
84.8%
Better than 84% of models compared
HLE
Humanity's Last Exam
19.1%
Better than 79% 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 84% of models compared
SciCode
Python programming for scientific computing
42.6%
Better than 81% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
34.8%
Last updated Jul 17, 2026
Artificial AnalysisBetter than 80% of models compared
