models/minimax/minimax-m2-her
M
minimax·active

MiniMax: MiniMax M2-her

minimax's efficiency model. Context window: 66K tokens.

Overall score
2.62
/5.00 · ranked #104
Input
$0.300
per 1M tokens
Output
$1.20
per 1M tokens
Context
66K
tokens
Blended
$0.975
3:1 out:in ratio

Price drops, new benchmarks, model updates. Stay current on MiniMax: MiniMax M2-her.

One email per change. Unsubscribe anytime.

modelpicker.aipowered by live benchmark data

Scores by test

Methodology →
Structured Output
4.0
Strategic Analysis
1.0
Constrained Rewriting
1.0
Creative Problem Solving
2.0
Tool Calling
Faithfulness
5.0
Classification
4.0
Long Context
4.0
Safety Calibration
1.0
Persona Consistency
4.0
Agentic Planning
3.0
Multilingual
3.0
Tabular Data
2.0

What you need to know

MiniMax M2-her is a specialized model optimized for data integrity and formatting rather than reasoning. Its primary differentiator is a perfect 5/5 score in faithfulness, meaning it excels at adhering to provided source material without hallucinating. This reliability extends to structured output and classification, both scoring 4/5, making it a viable tool for extracting clean data from unstructured text.

The model struggles significantly with complex cognitive tasks. It fails in strategic analysis and constrained rewriting, both scoring 1/5, and shows poor safety calibration. While it handles long context well (4/5), its inability to perform high-level reasoning or follow strict rewriting constraints limits its utility as a general-purpose assistant.

At a blended cost of $0.975/MTok, the pricing is competitive, but the value proposition is narrow. You are paying for a reliable extractor, not a problem solver. Given its rank of 104 out of 105 models, it is an underperformer in general intelligence but a specialist in precision.

Use this model if your pipeline requires high faithfulness, classification, or structured data extraction from long documents. Skip this model if you need strategic planning, creative rewriting, or a model with robust safety guardrails.

Strengths — Top 3

Faithfulness5.0/5.0
Structured Output4.0/5.0
Classification4.0/5.0

Relative weaknesses — Bottom 3

Strategic Analysis1.0/5.0
Constrained Rewriting1.0/5.0
Safety Calibration1.0/5.0

Similar models

MLlama 4 Maverick$0.4873.15MMistral Small 3.1 24B$0.5042.77IIBM: Granite 4.0 Micro$0.0882.54OGPT-4o$8.133.46