MiniMax M2 from MiniMax is a large language model for multilingual tasks, reasoning, coding, and long-chain tool calling in agent workflows.
Capabilities, design details, and architectural traits
MiniMax M2 is a large language model built for agents and code. Its documented identity centers on multilingual work, reasoning, coding, and long-chain tool use.
| Distinctive trait | What is explicitly documented |
|---|---|
| Born for Agents and Code | The model is described as built for agent workflows and code tasks. |
| Stable tool calling | It is presented as handling complex, long-chain tool-calling tasks with stable execution. |
| End-to-end development workflows | The model is positioned for development flows and programming use cases. |
| Strong multilingual capability | The model card states strong multilingual capabilities. |
The model is framed around agent use rather than generic chat. The official announcement says it coordinates calls to Shell, Browser, Python code interpreter, and MCP tools.
The model card describes it as a large language model with strong multilingual capabilities and solid performance on reasoning and coding benchmarks. That makes its identity broader than coding alone, but still centered on agentic software work and multilingual use.
Independent evaluations · Artificial Analysis
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | |||
|---|---|---|---|
| General Info | |||
| Provider | MiniMax | Anthropic | Anthropic |
| Release Date | October 26, 2025 | July 24, 2026 | June 9, 2026 |
| Knowledge Cutoff | - | May 2026 | - |
| Context & Limits | |||
| Context Window | 205K | 1M Best Context Window | 1M Best Context Window |
| Pricing (per 1M tokens) | |||
| Input Pricing | $0.30 Best Input Pricing | $5 | $10 |
| Output Pricing | $1.20 Best Output Pricing | $25 | $50 |
| Modalities | |||
| Inputs | text | textimage | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 28.9 | 63.1 Best Intelligence Index | 62.1 |
| Coding Index | - | 78.0 Best Coding Index | 76.5 |
| Agentic Index | - | 59.2 Best Agentic Index | 56.6 |
Graduate-level reasoning and expert Q&A evaluation.
Extremely difficult logical reasoning and knowledge.
Logical reasoning over long context windows.
Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.
