Moonshot AI benchmarks.
A lab-level profile for Moonshot AI, covering tracked models, category leaders, open/proprietary mix, speed, value, source coverage, and portfolio depth.
Lab rank
#1
By available Arena average
Models tracked
7
7 open-weight models
Portfolio coverage
46%
Average matched benchmark signals
Fastest model
1.08s
Kimi K2.5 Thinking
Lab profile
Portfolio shape, leaders, and model coverage.
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
Moonshot AI has 7 tracked benchmark profiles.
The portfolio combines 0 proprietary models and 7 open-weight models. Its average available Arena rank is 48.7, with a best category rank of #17. Average profile coverage is 46%, so model-level gaps remain visible in the cards below.
Best Arena model
Kimi K2.6
Best category rank #17
Highest coverage
Kimi K2.5 Thinking
89% matched signals
Fastest response
Kimi K2.5 Thinking
1.08s first token
Access mix
Open versus proprietary
Proprietary
0 / 0%
Open weights
7 / 100%
Value leader
Kimi K2 0905 PreviewCategory leaders
Best model by benchmark lens.
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
Kimi K2 0905 Preview
value index
Coding
Code Arena, SWE-bench, and output speed
Kimi K2.5 Thinking
coding index
Agents
Search, document, code, and latency
Kimi K2 0905 Preview
agent proxy
Reasoning
Text, document, vision, and mode signals
Kimi K2 Thinking Turbo
reasoning proxy
Context
Document, search, and text proxy
Kimi K2.5 Instant
context proxy
Moonshot AI value ranking table
Models from this lab with both quality and commercial price matches.
Top 4 of 4
| Rank | Model | Index | Price | Latency | Speed | Quality | Sources |
|---|---|---|---|---|---|---|---|
| #23 | 80value index | $1.08blended / 1M tokens | 1.19stime to first token | 37 tok/soutput speed | 83quality signal | ArenaArtificial Analysis | |
| #51 | 76value index | $1.71blended / 1M tokens | 1.12stime to first token | 48 tok/soutput speed | 76quality signal | ArenaArtificial Analysis | |
| #81 | 73value index | $1.71blended / 1M tokens | 1.17stime to first token | 46 tok/soutput speed | 70quality signal | ArenaArtificial Analysis | |
| #90 | 72value index | $1.20blended / 1M tokens | 1.08stime to first token | 50 tok/soutput speed | 68quality signal | ArenaArtificial Analysis |
Model portfolio
Moonshot AI model coverage map.
Every tracked model keeps its best Arena rank, coverage score, commercial metrics, and suite placement visible in one scannable grid.
Kimi K2.6
kimi-k2.6
Coverage
78%
Best Arena
#17
Code
Value
#51
value index
Coding
#33
coding index
Latency
1.12s
48 tok/s
Kimi K2.5 Thinking
kimi-k2.5-thinking
Coverage
89%
Best Arena
#25
Docs
Value
#90
value index
Coding
#23
coding index
Latency
1.08s
50 tok/s
Kimi K2.7 Code
kimi-k2.7-code
Coverage
44%
Best Arena
#25
Code
Value
#81
value index
Coding
#43
coding index
Latency
1.17s
46 tok/s
Kimi K2.5 Instant
kimi-k2.5-instant
Coverage
33%
Best Arena
#41
Code
Value
Not listed
No price match
Coding
#42
coding index
Latency
Not listed
Not listed
Kimi K2 Thinking Turbo
kimi-k2-thinking-turbo
Coverage
22%
Best Arena
#73
Code
Value
Not listed
No price match
Coding
#71
coding index
Latency
Not listed
Not listed
Kimi K2 0905 Preview
kimi-k2-0905-preview
Coverage
44%
Best Arena
#98
Text
Value
#23
value index
Coding
#131
coding index
Latency
1.19s
37 tok/s
Kimi K2 0711 Preview
kimi-k2-0711-preview
Coverage
11%
Best Arena
#101
Text
Value
Not listed
No price match
Coding
Not listed
No coding index
Latency
Not listed
Not listed
