Xiaomi
MiMo-V2.5-Pro (Non-reasoning)
MiMo V2.5 Pro delivers significant improvements over its predecessor, MiMo-V2-Pro, in general agentic capabilities, complex software engineering, and long-horizon tasks. MiMo-V2.5-Pro is a 1.02T-parameter Mixture-of-Experts model with 42B active parameters, built on a hybrid-attention architecture with a 1M-token context window.
Xiaomi model releasesModel Snapshot
TypeLanguage
ReleaseApr 22, 2026
Context1,048,576
Tagsreasoning, tool-use, implicit-caching
Overall
Rank #178 across 600
27.9
Coding
Rank #61 across 266
60.2
Blended Price
Rank #137 across 379
$0.544/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 Speed36.8 tok/s
First Token2.25s
Max Output131,072
Pricing
Blended$0.544/M
Input$0.435/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 27.9 | #178 |
| Artificial Analysis Coding Index | coding | 60.2 | #61 |
| GPQA | reasoning | 76.2% | #204 |
| Humanity's Last Exam | reasoning | 13.3% | #165 |
| SciCode |