Qwen: Qwen3.6 Max Preview
Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic co…
qwen/qwen3.6-max-preview-20260420
Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and...
Specifications & capabilities
- Input
- text
- Output
- text
- Context window · tokens
- 262144
Evaluations
41–60 / 63
1,470.047
- source id
- lmarena
- leaderboard name
- LMArena Text Coding
- dimension
- general
- metric
- Arena rating
- rank
- 69
- sample size
- 1600
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1454.9003498832108
- confidence upper
- 1485.1930422958976
Original result ↗1,465.204
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Software And It Services
- dimension
- general
- metric
- Arena rating
- rank
- 69
- sample size
- 2241
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1452.5079029117876
- confidence upper
- 1477.9004688628993
Original result ↗1,483.702
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Hard Prompts English
- dimension
- style
- metric
- Arena rating
- rank
- 70
- sample size
- 1699
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1469.093840178264
- confidence upper
- 1498.3108086079105
Original result ↗1,454.076
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Russian
- dimension
- style
- metric
- Arena rating
- rank
- 70
- sample size
- 583
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1429.131236981928
- confidence upper
- 1479.0200741955273
Original result ↗1,447.207
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Instruction Following
- dimension
- factuality
- metric
- Arena rating
- rank
- 70
- sample size
- 1878
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1434.2939184897612
- confidence upper
- 1460.1200102258401
Original result ↗1,471.584
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Hard Prompts
- dimension
- factuality
- metric
- Arena rating
- rank
- 71
- sample size
- 3542
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1462.1171382146003
- confidence upper
- 1481.0499740570417
Original result ↗1,465.966
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Multi Turn
- dimension
- style
- metric
- Arena rating
- rank
- 71
- sample size
- 925
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1445.9368271448566
- confidence upper
- 1485.9950326632852
Original result ↗1,450.609
- source id
- lmarena
- leaderboard name
- LMArena Text English
- dimension
- general
- metric
- Arena rating
- rank
- 71
- sample size
- 2458
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1438.6394808283062
- confidence upper
- 1462.579302562106
Original result ↗1,485.552
- source id
- lmarena
- leaderboard name
- LMArena Text Chinese
- dimension
- general
- metric
- Arena rating
- rank
- 73
- sample size
- 351
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1454.392379914384
- confidence upper
- 1516.7113007111532
Original result ↗1,460.748
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality English
- dimension
- factuality
- metric
- Arena rating
- rank
- 73
- sample size
- 2458
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1449.5656445003578
- confidence upper
- 1471.9302057346113
Original result ↗1,455.684
- source id
- lmarena
- leaderboard name
- LMArena Text Hard Prompts English
- dimension
- general
- metric
- Arena rating
- rank
- 73
- sample size
- 1699
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1441.111839654757
- confidence upper
- 1470.256083142469
Original result ↗1,482.224
- source id
- lmarena
- leaderboard name
- LMArena Webdev Overall
- dimension
- coding
- metric
- Arena rating
- rank
- 75
- sample size
- 2674
- evaluated at
- 2026-11-10T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1469.638299942555
- confidence upper
- 1494.808965928597
Original result ↗1,482.224
- source id
- lmarena
- leaderboard name
- LMArena Webdev Webdev
- dimension
- coding
- metric
- Arena rating
- rank
- 75
- sample size
- 2674
- evaluated at
- 2026-11-10T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1469.638299942555
- confidence upper
- 1494.808965928597
Original result ↗1,426.526
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Entertainment And Sports And Media
- dimension
- style
- metric
- Arena rating
- rank
- 75
- sample size
- 999
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1407.2877374861903
- confidence upper
- 1445.76358407933
Original result ↗1,484.668
- source id
- lmarena
- leaderboard name
- LMArena Text Factuality Industry Software And It Services
- dimension
- factuality
- metric
- Arena rating
- rank
- 76
- sample size
- 2241
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1472.7593073808305
- confidence upper
- 1496.5768255611138
Original result ↗1,473.15
- source id
- lmarena
- leaderboard name
- LMArena Webdev Webdev React
- dimension
- coding
- metric
- Arena rating
- rank
- 76
- sample size
- 2291
- evaluated at
- 2026-11-10T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1459.5607287297241
- confidence upper
- 1486.7399944850506
Original result ↗1,461.618
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Legal And Government
- dimension
- style
- metric
- Arena rating
- rank
- 76
- sample size
- 398
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1431.057991478672
- confidence upper
- 1492.1789396497104
Original result ↗1,450.483
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Business And Management And Financial Operations
- dimension
- style
- metric
- Arena rating
- rank
- 78
- sample size
- 1067
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1432.1343768768238
- confidence upper
- 1468.8309994821911
Original result ↗1,492.301
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Chinese
- dimension
- style
- metric
- Arena rating
- rank
- 79
- sample size
- 351
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1460.9805239375032
- confidence upper
- 1523.6222367217424
Original result ↗1,450.808
- source id
- lmarena
- leaderboard name
- LMArena Text French
- dimension
- general
- metric
- Arena rating
- rank
- 79
- sample size
- 214
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Qwen3.6-Max-Preview
- confidence lower
- 1409.2562757258843
- confidence upper
- 1492.3597741069668
Original result ↗Safety assessments
1–1 / 1
26 / 100
- source id
- stanfordFMTI
- canonical model id
- qwen/qwen3.6-max-preview-20260420
- 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
Explore more models