MiniMax
MiniMax-M2
MiniMax-M2 redefines efficiency for agents. It is a compact, fast, and cost-effective MoE model (230 billion total parameters with 10 billion active parameters) built for elite performance in coding and agentic tasks, all while maintaining powerful general intelligence.
MiniMax model releasesModel Snapshot
TypeLanguage
ReleaseOct 27, 2025
Context204,800
Tagsreasoning, tool-use
Overall
Rank #176 across 600
28.3
Coding
No rank
n/a
Blended Price
Rank #128 across 379
$0.525/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Max Output131,072
Streaming speed is not measured for this model yet.
Pricing
Blended$0.525/M
Input$0.300/M
Output$1.20/M
Catalog$0.300/M in / $1.20/M out
Metadata
Modalities
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 28.3 | #176 |
| Artificial Analysis Math Index | math | 78.3 | #74 |
| MMLU-Pro | reasoning | 82.0% | #69 |
| GPQA | reasoning | 77.7% | #183 |
| Humanity's Last Exam |