Qwen3 Max Preview

Qwen3-Max-Preview shows substantial gains over the 2.5 series in overall capability, with significant enhancements in Chinese-English text understanding, complex instruction following, handling of su…

vercelAIGatewayCatalog/alibaba/qwen3-max-preview

Qwen3-Max-Preview shows substantial gains over the 2.5 series in overall capability, with significant enhancements in Chinese-English text understanding, complex instruction following, handling of subjective open-ended tasks, multilingual ability, and tool invocation; model knowledge hallucinations are reduced.

Specifications & capabilities

Input
text
Output
text
Context window · tokens
262144
Max output · tokens
32768

Evaluations

21–40 / 74

LMArena

1,454.419

source id
lmarena
leaderboard name
LMArena Text Expert
dimension
general
metric
Arena rating
rank
81
sample size
1340
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1438.2526531429226
confidence upper
1470.586059949193
Original result ↗

LMArena

1,448.964

source id
lmarena
leaderboard name
LMArena Text Style Control German
dimension
style
metric
Arena rating
rank
81
sample size
594
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1423.9863480444465
confidence upper
1473.9416463974594
Original result ↗

LMArena

1,398.54

source id
lmarena
leaderboard name
LMArena Text Japanese
dimension
general
metric
Arena rating
rank
81
sample size
437
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1370.1900026311405
confidence upper
1426.8903829957378
Original result ↗

LMArena

1,432.758

source id
lmarena
leaderboard name
LMArena Text Factuality Non English
dimension
factuality
metric
Arena rating
rank
82
sample size
3747
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1423.5538984039792
confidence upper
1441.9616044701174
Original result ↗

LMArena

1,438.202

source id
lmarena
leaderboard name
LMArena Text Longer Query
dimension
general
metric
Arena rating
rank
83
sample size
6139
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1430.2920719334982
confidence upper
1446.1116749217697
Original result ↗

LMArena

1,444.365

source id
lmarena
leaderboard name
LMArena Text Industry Mathematical
dimension
general
metric
Arena rating
rank
84
sample size
1323
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1428.686959308247
confidence upper
1460.0431978196625
Original result ↗

LMArena

1,454.505

source id
lmarena
leaderboard name
LMArena Text Factuality Longer Query
dimension
factuality
metric
Arena rating
rank
86
sample size
1035
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1437.3139892578797
confidence upper
1471.6962555010243
Original result ↗

LMArena

1,448.788

source id
lmarena
leaderboard name
LMArena Text French
dimension
general
metric
Arena rating
rank
86
sample size
437
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1420.257800070155
confidence upper
1477.3181249504298
Original result ↗

LMArena

1,453.701

source id
lmarena
leaderboard name
LMArena Text Factuality English
dimension
factuality
metric
Arena rating
rank
87
sample size
2537
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1442.6238386208224
confidence upper
1464.7781246830336
Original result ↗

LMArena

1,427.616

source id
lmarena
leaderboard name
LMArena Text Russian
dimension
general
metric
Arena rating
rank
87
sample size
1864
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1414.1974615388035
confidence upper
1441.0335422489343
Original result ↗

LMArena

1,458.532

source id
lmarena
leaderboard name
LMArena Text Industry Software And It Services
dimension
general
metric
Arena rating
rank
88
sample size
9316
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1451.8720998897452
confidence upper
1465.1924784889197
Original result ↗

LMArena

1,404.509

source id
lmarena
leaderboard name
LMArena Text Industry Entertainment And Sports And Media
dimension
general
metric
Arena rating
rank
89
sample size
4943
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1395.8895097467735
confidence upper
1413.1278091066629
Original result ↗

LMArena

1,445.295

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Business And Management And Financial Operations
dimension
style
metric
Arena rating
rank
90
sample size
5129
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1436.745430435709
confidence upper
1453.844350992128
Original result ↗

LMArena

1,441.878

source id
lmarena
leaderboard name
LMArena Text Factuality Exclude Ties
dimension
factuality
metric
Arena rating
rank
90
sample size
5177
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1432.6252139616834
confidence upper
1451.130941325747
Original result ↗

LMArena

1,419.464

source id
lmarena
leaderboard name
LMArena Text Instruction Following
dimension
general
metric
Arena rating
rank
91
sample size
7295
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1412.146580837366
confidence upper
1426.7820157566634
Original result ↗

LMArena

1,442.193

source id
lmarena
leaderboard name
LMArena Text English
dimension
general
metric
Arena rating
rank
92
sample size
11454
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1436.083898365347
confidence upper
1448.3020389703943
Original result ↗

LMArena

1,455.877

source id
lmarena
leaderboard name
LMArena Text Coding
dimension
general
metric
Arena rating
rank
93
sample size
5356
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1447.5500417666344
confidence upper
1464.2037731788341
Original result ↗

LMArena

1,441.578

source id
lmarena
leaderboard name
LMArena Text Factuality Overall
dimension
factuality
metric
Arena rating
rank
93
sample size
7545
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1434.836154330636
confidence upper
1448.3194458443722
Original result ↗

LMArena

1,447.853

source id
lmarena
leaderboard name
LMArena Text Hard Prompts English
dimension
general
metric
Arena rating
rank
94
sample size
5809
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1439.8691065013286
confidence upper
1455.837008752728
Original result ↗

LMArena

1,401.972

source id
lmarena
leaderboard name
LMArena Text Creative Writing
dimension
general
metric
Arena rating
rank
96
sample size
3715
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1392.0474123497581
confidence upper
1411.8970359633383
Original result ↗

Safety assessments

1–1 / 1

Foundation Model Transparency Index 2025 ↗

26 / 100

source id
stanfordFMTI
canonical model id
vercelAIGatewayCatalog/alibaba/qwen3-max-preview
taxonomy
transparency
hazard category
transparency
hazard name
Organization transparency
policy area
Alibaba
assessment type
organization-level disclosure
metric
disclosure_score
result label
26 / 100
sample size
100
updated at
2026-11-09T18:08:05.227Z

Original sources

1–2 / 2

GitHub · Catalog ↗

LMArena · Catalog ↗

Source links

1–2 / 2

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace