#14
73value index
Price
$1.35blended / 1M tokens
Latency
2.66stime to first token
Speed
44 tok/soutput speed
Quality
69quality signal
ArenaArtificial Analysis
Thoughts on AI, technology, and the future we're building.
New posts every week
Thoughts on AI, technology, and the future we're building.
New posts every week
A lab-level profile for Xiaomi, covering tracked models, category leaders, open/proprietary mix, speed, value, source coverage, and portfolio depth.
Lab rank
#2
By available Arena average
Models tracked
5
3 open-weight models
Portfolio coverage
53%
Average matched benchmark signals
Fastest model
1.32s
MiMo V2 Flash
Lab profile
The lab page now starts with the portfolio read, then drills into category leaders, value rankings, and model-level coverage rather than repeating source panels.
Portfolio read
The portfolio combines 2 proprietary models and 3 open-weight models. Its average available Arena rank is 44.1, with a best category rank of #15. Average profile coverage is 53%, so model-level gaps remain visible in the cards below.
Best Arena model
MiMo V2.5 Pro
Best category rank #15
Highest coverage
MiMo V2.5
67% matched signals
Fastest response
MiMo V2 Flash
1.32s first token
Category leaders
Each card shows the highest-ranked model from this lab in a composite benchmark suite, with the global rank and index left intact.
Value
Quality, price, latency, and speed
MiMo V2.5 Pro
value index
Coding
Code Arena, SWE-bench, and output speed
MiMo V2.5 Pro
coding index
Agents
Search, document, code, and latency
MiMo V2 Omni
agent proxy
Reasoning
Text, document, vision, and mode signals
MiMo V2.5 Pro
reasoning proxy
Context
Document, search, and text proxy
MiMo V2.5 Pro
context proxy
Models from this lab with both quality and commercial price matches.
Top 4 of 4
| Rank | Model | Index | Price | Latency | Speed | Quality | Sources |
|---|---|---|---|---|---|---|---|
| #14 | 73value index | $1.35blended / 1M tokens | 2.66stime to first token | 44 tok/soutput speed | 69quality signal | ArenaArtificial Analysis | |
| #30 | 66value index | $0.175blended / 1M tokens | 2.25stime to first token | 89 tok/soutput speed | 53quality signal | ArenaArtificial Analysis | |
| #33 | 65value index | $1.50blended / 1M tokens | 2.99stime to first token | 46 tok/soutput speed | 55quality signal | ArenaArtificial Analysis | |
| #39 | 62value index | $0.150blended / 1M tokens | 1.32stime to first token | 131 tok/soutput speed | 44quality signal | ArenaArtificial Analysis |
Model portfolio
Every tracked model keeps its best Arena rank, coverage score, commercial metrics, and suite placement visible in one scannable grid.
MiMo V2.5 Pro
mimo-v2.5-pro
Coverage
56%
Best Arena
#15
Code
Value
#14
value index
Coding
#27
coding index
Latency
2.66s
44 tok/s
MiMo V2.5
mimo-v2.5
Coverage
67%
Best Arena
#23
Code
Value
#30
value index
Coding
#38
coding index
Latency
2.25s
89 tok/s
MiMo V2 Pro
mimo-v2-pro
Coverage
56%
Best Arena
#28
Code
Value
#33
value index
Coding
#40
coding index
Latency
2.99s
46 tok/s
MiMo V2 Omni
mimo-v2-omni
Coverage
44%
Best Arena
#48
Vision
Value
Not listed
No price match
Coding
#89
coding index
Latency
2.69s
87 tok/s
MiMo V2 Flash
mimo-v2-flash (non-thinking)
Coverage
44%
Best Arena
#63
Code
Value
#39
value index
Coding
#66
coding index
Latency
1.32s
131 tok/s