Xiaomi MiMo-V2.5-Pro is an open-source Mixture-of-Experts model from Xiaomi for agentic coding, long-horizon tasks, and 1M-token context.
Capabilities, design details, and architectural traits
MiMo-V2.5-Pro is built for long, tool-heavy work. It is designed for agentic tasks, complex software engineering, and long-horizon trajectories that stay coherent across very large context windows.
| Differentiator | Documented trait |
|---|---|
| 1M-token context | Supports up to 1M tokens of context. |
| Mixture-of-Experts design | Uses a 1.02T-parameter MoE model with 42B active parameters. |
| Hybrid attention + MTP | Uses hybrid attention and Multi-Token Prediction from the MiMo-V2-Flash design. |
| Long tool-call trajectories | Can sustain complex trajectories spanning thousands of tool calls. |
The model pairs very long context with agent-focused behavior. That makes it different from a standard general chat model, because the documented emphasis is on extended task execution and strong instruction following across long runs.
It is also open-sourced and presented as the most capable MiMo model in the series. The model card describes it as suited to the most demanding agentic, software engineering, and long-horizon tasks.
Independent evaluations · Artificial Analysis
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | |||
|---|---|---|---|
| General Info | |||
| Provider | Xiaomi | Anthropic | Anthropic |
| Release Date | April 22, 2026 | July 24, 2026 | June 9, 2026 |
| Knowledge Cutoff | - | May 2026 | - |
| Context & Limits | |||
| Context Window | 1.0M Best Context Window | 1M | 1M |
| Pricing (per 1M tokens) | |||
| Input Pricing | $0.43 Best Input Pricing | $5 | $10 |
| Output Pricing | $0.87 Best Output Pricing | $25 | $50 |
| Modalities | |||
| Inputs | text | textimage | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 42.9 | 63.1 Best Intelligence Index | 62.1 |
| Coding Index | 60.2 | 78.0 Best Coding Index | 76.5 |
| Agentic Index | 29.5 | 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.
