Xiaomi
MiMo-V2.6-Flash
MiMo V2.6 Flash is Xiaomi's efficient multimodal reasoning model for coding, automation, and everyday agent workflows. It accepts text, images, audio, and video within a 1M-token context window, with up to 128K tokens of output. Deep thinking, tool calling, JSON mode, and prompt caching make it suitable for applications that need multimodal understanding at a lower token cost.
Xiaomi model releasesModel Snapshot
TypeLanguage
ReleaseSep 21, 2026
Context1,048,576
Tagsimplicit-caching, reasoning, structured-output, tool-use
Overall
Rank #77 across 703
37.9
Coding
No rank
n/a
Blended Price
Rank #62 across 428
$0.175/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
Output Speed52.1 tok/s
First Token3.10s
Max Output131,072
Pricing
Blended$0.175/M
Input$0.140/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 37.9 | #77 |
| Humanity's Last Exam | reasoning | 35.1% | #100 |
| SciCode | coding, reasoning | 51.3% | #78 |
| Output Speed | speed | 52.1 tok/s | #140 |
| Time to First Token |