Benchmark suiteLatest source data: Sep 1, 2026Checked: September 2, 2026

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.

All labs

Lab rank

#4

By available Arena average

Models tracked

6

5 open-weight models

Portfolio coverage

39%

Average matched benchmark signals

Fastest model

1.31s

Kimi K2.7 Code

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 6 tracked benchmark profiles.

Lab #4

The portfolio combines 1 proprietary models and 5 open-weight models. Its average available Arena rank is 50.6, with a best category rank of #3. Average profile coverage is 39%, so model-level gaps remain visible in the cards below.

Best Arena model

Kimi K3 Max

Best category rank #3

Highest coverage

Kimi K2.6

56% matched signals

Fastest response

Kimi K2.7 Code

1.31s first token

Access mix

Open versus proprietary

Proprietary

1 / 17%

Open weights

5 / 83%

Value leader

Kimi K2.6

Category 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 K2.6

#2467

value index

Coding

Code Arena, SWE-bench, and output speed

Kimi K3 Max

#395

coding index

Agents

Search, document, code, and latency

Kimi K3 Max

#695

agent proxy

Reasoning

Text, document, vision, and mode signals

Kimi K3 Max

#1378

reasoning proxy

Context

Document, search, and text proxy

Kimi K3 Max

#1678

context proxy

Moonshot AI value ranking table

Models from this lab with both quality and commercial price matches.

Top 3 of 3

#24
Kimi K2.6

kimi-k2.6

Moonshot AIOpen weights
67value index
Price
$1.71blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
52quality signal
ArenaArtificial Analysis
#42
Kimi K2.5 Thinking

kimi-k2.5-thinking

Moonshot AIOpen weights
58value index
Price
$1.20blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
38quality signal
ArenaArtificial Analysis
#44
Kimi K2.7 Code

kimi-k2.7-code

Moonshot AIOpen weights
58value index
Price
$1.71blended / 1M tokens
Latency
1.31stime to first token
Speed
46 tok/soutput speed
Quality
41quality 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 K3 Max

kimi-k3-max

Proprietary

Coverage

22%

Best Arena

#3

Code

Value

Not listed

No price match

Coding

#3

coding index

Latency

Not listed

Not listed

Not listed

Kimi K2.6

kimi-k2.6

Open weights

Coverage

56%

Best Arena

#25

Docs

Value

#24

value index

Coding

#32

coding index

Latency

Not listed

Not listed

$1.71

Kimi K2.5 Thinking

kimi-k2.5-thinking

Open weights

Coverage

56%

Best Arena

#31

Docs

Value

#42

value index

Coding

#56

coding index

Latency

Not listed

Not listed

$1.20

Kimi K2.7 Code

kimi-k2.7-code

Open weights

Coverage

44%

Best Arena

#45

Code

Value

#44

value index

Coding

#51

coding index

Latency

1.31s

46 tok/s

$1.71

Kimi K2.5 Instant

kimi-k2.5-instant

Open weights

Coverage

33%

Best Arena

#52

Vision

Value

Not listed

No price match

Coding

#65

coding index

Latency

Not listed

Not listed

Not listed

Kimi K2 Thinking Turbo

kimi-k2-thinking-turbo

Open weights

Coverage

22%

Best Arena

#98

Text

Value

Not listed

No price match

Coding

#101

coding index

Latency

Not listed

Not listed

Not listed