Qwen3 Max Preview
Closed weights. No supported local deployment or GPU requirement is published.
GeekRadar / The comparison desk
COMPARE.
AI modelsQwen3 Max Preview
AI model Released
- Context window
- 262,144 tokens
- Maximum output
- 32,768 tokens
- Open weights
- No
Capability & preference
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
Recorded results
Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.
Arena text preference / chinesehuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,478.41 rating
Confidence interval: 1,465.33 – 1,491.49
2093 votes
- Category
- chinese
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,455.63 rating
Confidence interval: 1,447.31 – 1,463.95
5363 votes
- Category
- coding
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,401.07 rating
Confidence interval: 1,391.17 – 1,410.96
3733 votes
- Category
- creative_writing
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,442.04 rating
Confidence interval: 1,435.94 – 1,448.14
11492 votes
- Category
- english
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,435.80 rating
Confidence interval: 1,429.52 – 1,442.08
19405 votes
- Category
- exclude_ties
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,455.44 rating
Confidence interval: 1,439.31 – 1,471.57
1349 votes
- Category
- expert
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,449.89 rating
Confidence interval: 1,421.38 – 1,478.40
438 votes
- Category
- french
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,462.64 rating
Confidence interval: 1,437.83 – 1,487.46
597 votes
- Category
- german
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,448.05 rating
Confidence interval: 1,442.23 – 1,453.88
13554 votes
- Category
- hard_prompts
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,448.08 rating
Confidence interval: 1,440.11 – 1,456.05
5830 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,436.32 rating
Confidence interval: 1,427.79 – 1,444.85
5137 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,404.11 rating
Confidence interval: 1,395.51 – 1,412.71
4963 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,434.69 rating
Confidence interval: 1,420.45 – 1,448.94
1695 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,457.45 rating
Confidence interval: 1,448.09 – 1,466.81
4212 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,445.36 rating
Confidence interval: 1,429.76 – 1,460.95
1338 votes
- Category
- industry_mathematical
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,467.52 rating
Confidence interval: 1,451.72 – 1,483.33
1466 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,458.32 rating
Confidence interval: 1,451.67 – 1,464.97
9334 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,406.95 rating
Confidence interval: 1,399.15 – 1,414.76
6190 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,419.48 rating
Confidence interval: 1,412.17 – 1,426.78
7316 votes
- Category
- instruction_following
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,397.54 rating
Confidence interval: 1,369.24 – 1,425.85
438 votes
- Category
- japanese
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,398.12 rating
Confidence interval: 1,374.92 – 1,421.31
716 votes
- Category
- korean
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,438.05 rating
Confidence interval: 1,430.16 – 1,445.95
6157 votes
- Category
- longer_query
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,446.68 rating
Confidence interval: 1,431.76 – 1,461.61
1496 votes
- Category
- math
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,446.11 rating
Confidence interval: 1,437.06 – 1,455.16
4525 votes
- Category
- multi_turn
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,429.10 rating
Confidence interval: 1,423.55 – 1,434.66
15795 votes
- Category
- non_english
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,438.89 rating
Confidence interval: 1,434.39 – 1,443.40
27368 votes
- Category
- overall
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,439.92 rating
Confidence interval: 1,424.05 – 1,455.78
1453 votes
- Category
- polish
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,427.38 rating
Confidence interval: 1,413.97 – 1,440.78
1865 votes
- Category
- russian
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
Qwen3 Max Preview
1,462.09 rating
Confidence interval: 1,441.42 – 1,482.77
845 votes
- Category
- spanish
- Evaluated configuration
- Qwen3-Max-Preview
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,478.24 rating
Confidence interval: 1,465.16 – 1,491.32
2091 votes
- Category
- chinese
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,455.72 rating
Confidence interval: 1,447.40 – 1,464.03
5369 votes
- Category
- coding
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,401.10 rating
Confidence interval: 1,391.20 – 1,410.99
3730 votes
- Category
- creative_writing
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,442.14 rating
Confidence interval: 1,436.04 – 1,448.24
11497 votes
- Category
- english
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,435.74 rating
Confidence interval: 1,429.46 – 1,442.02
19405 votes
- Category
- exclude_ties
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,455.01 rating
Confidence interval: 1,438.87 – 1,471.14
1347 votes
- Category
- expert
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,449.36 rating
Confidence interval: 1,420.84 – 1,477.88
438 votes
- Category
- french
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,462.62 rating
Confidence interval: 1,437.81 – 1,487.44
597 votes
- Category
- german
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,447.98 rating
Confidence interval: 1,442.16 – 1,453.80
13554 votes
- Category
- hard_prompts
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,448.18 rating
Confidence interval: 1,440.21 – 1,456.15
5832 votes
- Category
- hard_prompts_english
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,436.57 rating
Confidence interval: 1,428.04 – 1,445.09
5138 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,403.98 rating
Confidence interval: 1,395.38 – 1,412.58
4961 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,434.48 rating
Confidence interval: 1,420.24 – 1,448.71
1696 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,457.45 rating
Confidence interval: 1,448.09 – 1,466.81
4209 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,445.38 rating
Confidence interval: 1,429.79 – 1,460.98
1338 votes
- Category
- industry_mathematical
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,467.60 rating
Confidence interval: 1,451.79 – 1,483.41
1466 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,458.41 rating
Confidence interval: 1,451.76 – 1,465.06
9341 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,406.92 rating
Confidence interval: 1,399.11 – 1,414.73
6184 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,419.52 rating
Confidence interval: 1,412.22 – 1,426.83
7315 votes
- Category
- instruction_following
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,398.19 rating
Confidence interval: 1,369.86 – 1,426.52
437 votes
- Category
- japanese
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,398.55 rating
Confidence interval: 1,375.33 – 1,421.77
714 votes
- Category
- korean
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,438.03 rating
Confidence interval: 1,430.13 – 1,445.93
6158 votes
- Category
- longer_query
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,445.97 rating
Confidence interval: 1,431.05 – 1,460.89
1495 votes
- Category
- math
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,446.32 rating
Confidence interval: 1,437.27 – 1,455.37
4528 votes
- Category
- multi_turn
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,428.98 rating
Confidence interval: 1,423.42 – 1,434.53
15792 votes
- Category
- non_english
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,438.82 rating
Confidence interval: 1,434.32 – 1,443.33
27370 votes
- Category
- overall
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,439.95 rating
Confidence interval: 1,424.09 – 1,455.81
1453 votes
- Category
- polish
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,427.46 rating
Confidence interval: 1,414.05 – 1,440.87
1866 votes
- Category
- russian
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
Qwen3 Max Preview
1,462.00 rating
Confidence interval: 1,441.31 – 1,482.68
845 votes
- Category
- spanish
- Evaluated configuration
- qwen3-max-preview
- Evaluation type
- human preference
Run it locally
API cost
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.
Qwen3 Max Preview
Capabilities
- Context window
- 262,144 tokens
- Maximum output
- 32,768 tokens
- Reasoning
- No
- Tool calling
- Yes
- Open weights
- No
- Knowledge cutoff
- 2025-04
- Model license
- Proprietary
Input modalities
- text
Output modalities
- text
0 selected Compare 0