MiMo-V2-Flash
Xiaomi MiMo-V2-Flash is a Xiaomi model built for long-context use, hybrid attention, and Multi-Token Prediction in the MiMo series and the V2.5 design.
Model Overview
Capabilities, design details, and architectural traits
MiMo-V2-Flash - hybrid-attention MiMo model
MiMo-V2-Flash is the series model behind the MiMo-V2.5 design. It is tied to the same long-context architecture and the same hybrid attention and Multi-Token Prediction pattern.
| Differentiator | Documented trait |
|---|---|
| Hybrid attention | Uses hybrid attention. |
| Multi-Token Prediction | Uses Multi-Token Prediction, shortened as MTP. |
| Long-context design | Serves as the base for the MiMo-V2.5 context and trajectory design. |
Shared design
The model is defined by its architecture rather than a chat-style role. The documented identity is its use in the MiMo series as the source of the hybrid attention and MTP setup.
Series role
MiMo-V2-Flash sits inside Xiaomi MiMo’s model family and connects directly to the V2.5 series. That makes it a structural model in the lineup, not just a named endpoint.
Benchmark Performance
Independent evaluations · Artificial Analysis
Accuracy & Capability Details
Compare Models Side-by-Side
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | |||
|---|---|---|---|
| General Info | |||
| Provider | Xiaomi | Anthropic | Anthropic |
| Release Date | December 16, 2025 | September 22, 2026 | September 28, 2026 |
| Knowledge Cutoff | - | - | Jun 2026 |
| Context & Limits | |||
| Context Window | 262K | 1M Best Context Window | 1M Best Context Window |
| Pricing (per 1M tokens) | |||
| Input Pricing | $0.10 Best Input Pricing | $4 | $2 |
| Output Pricing | $0.30 Best Output Pricing | $20 | $10 |
| Modalities | |||
| Inputs | text | textimagefile | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 16.0 | 57.6 Best Intelligence Index | 56.0 |
| Coding Index | 49.8 | - | - |
| Agentic Index | 12.0 | - | - |
Humanity's Last Exam
Extremely difficult logical reasoning and knowledge.
Long Context Reasoning
Logical reasoning over long context windows.
SciCode Benchmark
Scientific coding and mathematical modeling.
Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.
Explore more from Xiaomi
Other models by Xiaomi
Top AI Models
Leading alternatives by intelligence score
