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.
Added Mar 18, 2026
Context Window
204.8K
Max Output
131.1K
Input Price (Auto)
$0.31/1M
Output Price (Auto)
$1.26/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
49.6
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Coding Index
41.9
GPQA Diamond
Graduate-level scientific reasoning
87.4%
Better than 95% of models compared
HLE
Humanity's Last Exam
28.1%
Better than 95% of models compared
IFBench
Instruction-following benchmark
75.7%
Better than 95% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
84.8%
Better than 80% of models compared
AA-LCR
Long context reasoning evaluation
68.7%
Better than 94% of models compared
SciCode
Python programming for scientific computing
47.0%
Better than 95% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
39.4%
Better than 92% of models compared
Last updated May 15, 2026
Artificial Analysis
