Benchmark suiteLatest source data: Oct 16, 2026Checked: October 18, 2026

Alibaba benchmarks.

A lab-level profile for Alibaba, covering tracked models, category leaders, open/proprietary mix, speed, value, source coverage, and portfolio depth.

All labs

Lab rank

#8

By available Arena average

Models tracked

14

6 open-weight models

Portfolio coverage

36%

Average matched benchmark signals

Fastest model

0.99s

Qwen3.5 122b A10B

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

Alibaba has 14 tracked benchmark profiles.

Lab #8

The portfolio combines 8 proprietary models and 6 open-weight models. Its average available Arena rank is 56.2, with a best category rank of #2. Average profile coverage is 36%, so model-level gaps remain visible in the cards below.

Best Arena model

Qwen3.8 Max

Best category rank #2

Highest coverage

Qwen3.7 Plus

67% matched signals

Fastest response

Qwen3.5 122b A10B

0.99s first token

Access mix

Open versus proprietary

Proprietary

8 / 57%

Open weights

6 / 43%

Value leader

Qwen3.8 Max

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

Qwen3.8 Max

#479

value index

Coding

Code Arena, SWE-bench, and output speed

Qwen3.8 Max

#768

coding index

Agents

Search, document, code, and latency

Qwen3.5 122b A10B

#399

agent proxy

Reasoning

Text, document, vision, and mode signals

Qwen3.8 Max

#2566

reasoning proxy

Context

Document, search, and text proxy

Qwen3.8 Max

#2769

context proxy

Alibaba value ranking table

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

Top 10 of 10

#4
Qwen3.8 Max

qwen3.8-max

AlibabaProprietary
79value index
Price
$3.00blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
73quality signal
ArenaArtificial Analysis
#19
Qwen3.8 Flash Next

Qwen3.8-Flash-Next

AlibabaProprietary
68value index
Price
$0.230blended / 1M tokens
Latency
1.25stime to first token
Speed
51 tok/soutput speed
Quality
58quality signal
ArenaArtificial Analysis
#44
Qwen3.7 Plus

qwen3.7-plus

AlibabaProprietary
61value index
Price
$0.700blended / 1M tokens
Latency
1.69stime to first token
Speed
56 tok/soutput speed
Quality
44quality signal
ArenaArtificial Analysis
#56
Qwen3.5 122b A10B

qwen3.5-122b-a10b

AlibabaOpen weights
56value index
Price
$1.10blended / 1M tokens
Latency
0.99stime to first token
Speed
134 tok/soutput speed
Quality
32quality signal
ArenaArtificial Analysis
#67
Qwen3.8 27b

qwen3.8-27b

AlibabaOpen weights
52value index
Price
$1.13blended / 1M tokens
Latency
1.35stime to first token
Speed
43 tok/soutput speed
Quality
30quality signal
ArenaArtificial Analysis
#70
Qwen3.7 Max

Qwen3.7-Max (20260517)

AlibabaProprietary
51value index
Price
$3.75blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
31quality signal
ArenaArtificial Analysis
#71
Qwen3.5 27b

qwen3.5-27b

AlibabaOpen weights
50value index
Price
$0.825blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
24quality signal
ArenaArtificial Analysis
#74
Qwen3 VL 235b A22B Instruct

qwen3-vl-235b-a22b-instruct

AlibabaOpen weights
49value index
Price
$0.509blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
23quality signal
ArenaArtificial Analysis
#79
Qwen3.5 397b A17B

qwen3.5-397b-a17b

AlibabaOpen weights
46value index
Price
$1.35blended / 1M tokens
Latency
1.59stime to first token
Speed
55 tok/soutput speed
Quality
18quality signal
ArenaArtificial Analysis
#85
Qwen3.6 Plus

qwen3.6-plus

AlibabaProprietary
41value index
Price
$1.13blended / 1M tokens
Latency
Not listedtime to first token
Speed
Not listedoutput speed
Quality
11quality signal
ArenaArtificial Analysis

Model portfolio

Alibaba model coverage map.

Every tracked model keeps its best Arena rank, coverage score, commercial metrics, and suite placement visible in one scannable grid.

Qwen3.8 Max

qwen3.8-max

Proprietary

Coverage

56%

Best Arena

#2

Vision

Value

#4

value index

Coding

#7

coding index

Latency

Not listed

Not listed

$3.00

Qwen3.8 Flash Next

Qwen3.8-Flash-Next

Proprietary

Coverage

44%

Best Arena

#19

Code

Value

#19

value index

Coding

#22

coding index

Latency

1.25s

51 tok/s

$0.230

Qwen3.8 27b

qwen3.8-27b

Open weights

Coverage

67%

Best Arena

#29

Code

Value

#67

value index

Coding

#30

coding index

Latency

1.35s

43 tok/s

$1.13

Qwen3.7 Plus

qwen3.7-plus

Proprietary

Coverage

67%

Best Arena

#30

Docs

Value

#44

value index

Coding

#82

coding index

Latency

1.69s

56 tok/s

$0.700

Qwen3.7 Max Preview

qwen3.7-max-preview

Proprietary

Coverage

11%

Best Arena

#39

Text

Value

Not listed

No price match

Coding

Not listed

No coding index

Latency

Not listed

Not listed

Not listed

Qwen3.7 Max

Qwen3.7-Max (20260517)

Proprietary

Coverage

22%

Best Arena

#53

Code

Value

#70

value index

Coding

#45

coding index

Latency

Not listed

Not listed

$3.75

Qwen3.5 Max Preview

qwen3.5-max-preview

Proprietary

Coverage

11%

Best Arena

#57

Text

Value

Not listed

No price match

Coding

Not listed

No coding index

Latency

Not listed

Not listed

Not listed

Qwen3.5 397b A17B

qwen3.5-397b-a17b

Open weights

Coverage

67%

Best Arena

#60

Vision

Value

#79

value index

Coding

#83

coding index

Latency

1.59s

55 tok/s

$1.35

Qwen3.6 Max Preview

qwen3.6-max-preview

Proprietary

Coverage

22%

Best Arena

#60

Text

Value

Not listed

No price match

Coding

#56

coding index

Latency

Not listed

Not listed

Not listed

Qwen3.6 Plus

qwen3.6-plus

Proprietary

Coverage

33%

Best Arena

#70

Code

Value

#85

value index

Coding

#60

coding index

Latency

Not listed

Not listed

$1.13

Qwen3.5 122b A10B

qwen3.5-122b-a10b

Open weights

Coverage

44%

Best Arena

#75

Vision

Value

#56

value index

Coding

#52

coding index

Latency

0.99s

134 tok/s

$1.10

Qwen3.5 27b

qwen3.5-27b

Open weights

Coverage

22%

Best Arena

#79

Vision

Value

#71

value index

Coding

Not listed

No coding index

Latency

Not listed

Not listed

$0.825

Qwen3 VL 235b A22B Instruct

qwen3-vl-235b-a22b-instruct

Open weights

Coverage

22%

Best Arena

#83

Vision

Value

#74

value index

Coding

Not listed

No coding index

Latency

Not listed

Not listed

$0.509

Qwen3 VL 235b A22B Thinking

qwen3-vl-235b-a22b-thinking

Open weights

Coverage

11%

Best Arena

#97

Vision

Value

Not listed

No price match

Coding

Not listed

No coding index

Latency

Not listed

Not listed

Not listed