Xiaomi Models: Intelligence, Performance & Price
Artificial Analysis Intelligence Index
* Estimated
MiMo-V2.6-FlashMiMo-V2.5MiMo-V2.6-ProMiMo-V2.5-ProMiMo-V2.5-Pro (Non-reasoning)Output speed
Per Intelligence Index Task
Artificial Analysis has benchmarked 11 models from Xiaomi. Below is a comparison of the key metrics across these models.
- For intelligence, the top model from Xiaomi is MiMo-V2.6-Pro at 46.
- For output speed, the fastest model is MiMo-V2.6-Flash at 60 t/s.
- For latency, MiMo-V2.5-Pro (Non-reasoning) at 2.34s offers the lowest time to first answer token.
- For pricing, MiMo-V2.5-Pro at $0.05 offers the lowest cost per task. Prices vary up to 2.5x across models.
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Intelligence Index Task
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indexes
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · Higher is better
All Xiaomi Releases
MiMo-V2.6-Flash
1 model
38
Highest Intelligence
MiMo-V2.6-Pro
1 model
46
Highest Intelligence
MiMo-V2.5
1 model
25
Highest Intelligence
MiMo-V2.5-Pro
2 models
26
Highest Intelligence
MiMo-V2-Omni-0327
1 model
25
Highest Intelligence
MiMo-V2-Omni
1 model
24
Highest Intelligence
MiMo-V2-Pro
1 model
29
Highest Intelligence
MiMo-V2-Flash (Feb 2026)
1 model
22
Highest Intelligence
MiMo-V2-Flash
2 models
21
Highest Intelligence
Further details
Weights | Provider Benchmarks | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| MiMo-V2.6-Pro | Xiaomi | 46 | 1.0T 42B active at inference time | 1M | $0.2 | 44 |   | ||
| MiMo-V2.6-Flash | Xiaomi | 38 | 309B 15B active at inference time | 1M | $0.1 | 60 | | ||
| MiMo-V2-Pro | Xiaomi | 29 | - | 1M | - | - | Not available | - | |
| MiMo-V2.5-Pro | Xiaomi | 26 | 1.0T 42B active at inference time | 1M | $0.2 | 38 |   +2 | ||
| MiMo-V2.5 | Xiaomi | 25 | 310B 15B active at inference time | 1M | $0.1 | 46 | +2 | ||
| MiMo-V2-Omni-0327 | Xiaomi | 25 | - | 256k | - | - | Not available | - | |
| MiMo-V2-Omni | Xiaomi | 24 | - | 256k | - | - | Not available | - | |
| MiMo-V2-Flash (Feb 2026) | Xiaomi | 22 | 309B 15B active at inference time | 256k | - | - | - | ||
| MiMo-V2-Flash (Reasoning) | Xiaomi | 21 | 309B 15B active at inference time | 256k | $0.1 | - | | ||
| MiMo-V2.5-Pro (Non-reasoning) | Xiaomi | 18 | 1.0T 42B active at inference time | 1M | $0.2 | 30 |  +2 | ||
| MiMo-V2-Flash (Non-reasoning) | Xiaomi | 16 | 309B 15B active at inference time | 256k | - | - | - |