GeekRadar / The comparison desk
COMPARE.
AI models
alibaba

qwen-max-0919

Model evaluation

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

qwen-max-0919 1281.8 qwen-max-0919 · 95% interval 1276.2–1287.5 · 16,478 votes · 2026-10-15

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 · 2026-10-15 · rating

qwen-max-0919

1,253.97 rating

Confidence interval: 1,238.36 – 1,269.59

1421 votes

Category
chinese
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

qwen-max-0919

1,287.89 rating

Confidence interval: 1,276.78 – 1,299.01

2756 votes

Category
coding
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

qwen-max-0919

1,247.95 rating

Confidence interval: 1,235.96 – 1,259.95

2358 votes

Category
creative_writing
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

qwen-max-0919

1,292.49 rating

Confidence interval: 1,285.20 – 1,299.77

8347 votes

Category
english
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

qwen-max-0919

1,205.68 rating

Confidence interval: 1,197.12 – 1,214.24

10342 votes

Category
exclude_ties
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

qwen-max-0919

1,247.79 rating

Confidence interval: 1,229.80 – 1,265.78

1011 votes

Category
expert
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

qwen-max-0919

1,330.06 rating

Confidence interval: 1,288.88 – 1,371.25

183 votes

Category
french
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

qwen-max-0919

1,253.89 rating

Confidence interval: 1,227.70 – 1,280.09

438 votes

Category
german
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

qwen-max-0919

1,269.29 rating

Confidence interval: 1,260.08 – 1,278.50

4447 votes

Category
hard_prompts
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

qwen-max-0919

1,280.41 rating

Confidence interval: 1,269.13 – 1,291.69

2531 votes

Category
hard_prompts_english
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

qwen-max-0919

1,256.06 rating

Confidence interval: 1,243.30 – 1,268.82

2195 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

qwen-max-0919

1,240.51 rating

Confidence interval: 1,228.74 – 1,252.28

2396 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

qwen-max-0919

1,282.79 rating

Confidence interval: 1,264.80 – 1,300.79

1085 votes

Category
industry_legal_and_government
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

qwen-max-0919

1,279.03 rating

Confidence interval: 1,267.91 – 1,290.15

2975 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

qwen-max-0919

1,279.41 rating

Confidence interval: 1,266.34 – 1,292.48

1804 votes

Category
industry_mathematical
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

qwen-max-0919

1,259.01 rating

Confidence interval: 1,240.18 – 1,277.84

933 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

qwen-max-0919

1,290.67 rating

Confidence interval: 1,281.29 – 1,300.04

4410 votes

Category
industry_software_and_it_services
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

qwen-max-0919

1,270.24 rating

Confidence interval: 1,260.79 – 1,279.69

4631 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

qwen-max-0919

1,261.68 rating

Confidence interval: 1,253.75 – 1,269.60

6919 votes

Category
instruction_following
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

qwen-max-0919

1,205.02 rating

Confidence interval: 1,172.52 – 1,237.52

312 votes

Category
japanese
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

qwen-max-0919

1,141.54 rating

Confidence interval: 1,105.12 – 1,177.96

285 votes

Category
korean
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

qwen-max-0919

1,288.16 rating

Confidence interval: 1,276.37 – 1,299.96

2440 votes

Category
longer_query
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

qwen-max-0919

1,274.96 rating

Confidence interval: 1,263.09 – 1,286.84

2249 votes

Category
math
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

qwen-max-0919

1,276.69 rating

Confidence interval: 1,265.66 – 1,287.72

3105 votes

Category
multi_turn
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

qwen-max-0919

1,262.94 rating

Confidence interval: 1,255.54 – 1,270.33

8131 votes

Category
non_english
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

qwen-max-0919

1,281.84 rating

Confidence interval: 1,276.17 – 1,287.51

16478 votes

Category
overall
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

qwen-max-0919

1,274.05 rating

Confidence interval: 1,262.23 – 1,285.86

2432 votes

Category
russian
Evaluated configuration
qwen-max-0919
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

qwen-max-0919

1,289.93 rating

Confidence interval: 1,251.33 – 1,328.53

222 votes

Category
spanish
Evaluated configuration
qwen-max-0919
Evaluation type
human preference

Run it locally

Inference · memory estimate

qwen-max-0919

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Qwen