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

41–60 / 74

LMArena

1,462.441

source id
lmarena
leaderboard name
LMArena Text Factuality Hard Prompts
dimension
factuality
metric
Arena rating
rank
97
sample size
3637
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1452.9907080344965
confidence upper
1471.891119973598
Original result ↗

LMArena

1,457.025

source id
lmarena
leaderboard name
LMArena Text Style Control Industry Life And Physical And Social Science
dimension
style
metric
Arena rating
rank
98
sample size
4201
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1447.609220995305
confidence upper
1466.4400039651905
Original result ↗

LMArena

1,487.129

source id
lmarena
leaderboard name
LMArena Text Factuality Coding
dimension
factuality
metric
Arena rating
rank
100
sample size
835
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1468.5602712692082
confidence upper
1505.6987216541283
Original result ↗

LMArena

1,477.139

source id
lmarena
leaderboard name
LMArena Text Style Control Chinese
dimension
style
metric
Arena rating
rank
100
sample size
2087
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1464.015420443318
confidence upper
1490.2624897653363
Original result ↗

LMArena

1,435.013

source id
lmarena
leaderboard name
LMArena Text Industry Legal And Government
dimension
general
metric
Arena rating
rank
102
sample size
1689
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1420.7330666485611
confidence upper
1449.292214496528
Original result ↗

LMArena

1,384.705

source id
lmarena
leaderboard name
LMArena Text Style Control Korean
dimension
style
metric
Arena rating
rank
102
sample size
708
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1361.1349044899084
confidence upper
1408.2745213095855
Original result ↗

LMArena

1,458.398

source id
lmarena
leaderboard name
LMArena Text Style Control Hard Prompts
dimension
style
metric
Arena rating
rank
103
sample size
13516
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1452.5686307436904
confidence upper
1464.2273059133847
Original result ↗

LMArena

1,407.322

source id
lmarena
leaderboard name
LMArena Text Industry Writing And Literature And Language
dimension
general
metric
Arena rating
rank
103
sample size
6164
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1399.4977833154298
confidence upper
1415.1455691835636
Original result ↗

LMArena

1,467.246

source id
lmarena
leaderboard name
LMArena Text Factuality Hard Prompts English
dimension
factuality
metric
Arena rating
rank
105
sample size
943
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1449.6642719224865
confidence upper
1484.8278648066353
Original result ↗

LMArena

1,441.94

source id
lmarena
leaderboard name
LMArena Text Style Control Multi Turn
dimension
style
metric
Arena rating
rank
106
sample size
4512
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1432.8493191780212
confidence upper
1451.0298077855964
Original result ↗

LMArena

1,426.799

source id
lmarena
leaderboard name
LMArena Text Style Control Polish
dimension
style
metric
Arena rating
rank
106
sample size
1450
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1410.7648501427475
confidence upper
1442.8322823388648
Original result ↗

LMArena

1,461.868

source id
lmarena
leaderboard name
LMArena Text Style Control Expert
dimension
style
metric
Arena rating
rank
107
sample size
1340
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1445.7014395860733
confidence upper
1478.0340179367447
Original result ↗

LMArena

1,449.831

source id
lmarena
leaderboard name
LMArena Text Style Control French
dimension
style
metric
Arena rating
rank
107
sample size
437
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1421.1129883059243
confidence upper
1478.5480337587057
Original result ↗

LMArena

1,431.44

source id
lmarena
leaderboard name
LMArena Text Style Control Exclude Ties
dimension
style
metric
Arena rating
rank
107
sample size
19364
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1425.0940382051635
confidence upper
1437.7857571393988
Original result ↗

LMArena

1,442.574

source id
lmarena
leaderboard name
LMArena Text Style Control Longer Query
dimension
style
metric
Arena rating
rank
108
sample size
6139
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1434.628666686238
confidence upper
1450.5200576543823
Original result ↗

LMArena

1,432.688

source id
lmarena
leaderboard name
LMArena Text Style Control Math
dimension
style
metric
Arena rating
rank
108
sample size
1490
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1417.6761951429003
confidence upper
1447.699796438052
Original result ↗

LMArena

1,422.28

source id
lmarena
leaderboard name
LMArena Text Style Control Non English
dimension
style
metric
Arena rating
rank
108
sample size
15766
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1416.7079787815892
confidence upper
1427.8526535696622
Original result ↗

LMArena

1,384.448

source id
lmarena
leaderboard name
LMArena Text Style Control Japanese
dimension
style
metric
Arena rating
rank
108
sample size
437
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1355.8353680618338
confidence upper
1413.0611670679407
Original result ↗

LMArena

1,434.407

source id
lmarena
leaderboard name
LMArena Text Style Control Overall
dimension
style
metric
Arena rating
rank
109
sample size
27301
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1429.887664202256
confidence upper
1438.9271876950445
Original result ↗

LMArena

1,424.025

source id
lmarena
leaderboard name
LMArena Text Style Control Instruction Following
dimension
style
metric
Arena rating
rank
110
sample size
7295
evaluated at
2026-11-09T00:00:00.000Z
source model id
Qwen3-Max-Preview
confidence lower
1416.7280603192962
confidence upper
1431.322035879919
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