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) 1281.9 Qwen-Max (0919) · 95% interval 1276.2–1287.5 · 16,478 votes · 2026-10-28

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

Qwen-Max (0919)

1,253.92 rating

Confidence interval: 1,238.31 – 1,269.54

1421 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,287.79 rating

Confidence interval: 1,276.68 – 1,298.91

2756 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,247.80 rating

Confidence interval: 1,235.80 – 1,259.79

2358 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,292.54 rating

Confidence interval: 1,285.26 – 1,299.82

8347 votes

Oct 28, 2026

Category: english
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,205.67 rating

Confidence interval: 1,197.11 – 1,214.23

10342 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,247.75 rating

Confidence interval: 1,229.76 – 1,265.74

1011 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,330.38 rating

Confidence interval: 1,289.21 – 1,371.55

183 votes

Oct 28, 2026

Category: french
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,253.90 rating

Confidence interval: 1,227.67 – 1,280.12

438 votes

Oct 28, 2026

Category: german
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,269.30 rating

Confidence interval: 1,260.10 – 1,278.51

4447 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,280.52 rating

Confidence interval: 1,269.24 – 1,291.81

2531 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,256.02 rating

Confidence interval: 1,243.26 – 1,268.78

2195 votes

Oct 28, 2026

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 · 2026-10-28 · rating

Qwen-Max (0919)

1,240.46 rating

Confidence interval: 1,228.69 – 1,252.22

2396 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,283.05 rating

Confidence interval: 1,265.06 – 1,301.04

1085 votes

Oct 28, 2026

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 · 2026-10-28 · rating

Qwen-Max (0919)

1,279.05 rating

Confidence interval: 1,267.93 – 1,290.17

2975 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,279.42 rating

Confidence interval: 1,266.34 – 1,292.49

1804 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,258.96 rating

Confidence interval: 1,240.13 – 1,277.79

933 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,290.58 rating

Confidence interval: 1,281.21 – 1,299.96

4410 votes

Oct 28, 2026

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 · 2026-10-28 · rating

Qwen-Max (0919)

1,270.18 rating

Confidence interval: 1,260.73 – 1,279.63

4631 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,261.67 rating

Confidence interval: 1,253.74 – 1,269.59

6919 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,205.19 rating

Confidence interval: 1,172.66 – 1,237.73

312 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,141.50 rating

Confidence interval: 1,105.07 – 1,177.93

285 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,288.12 rating

Confidence interval: 1,276.33 – 1,299.91

2440 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,275.00 rating

Confidence interval: 1,263.13 – 1,286.88

2249 votes

Oct 28, 2026

Category: math
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,276.69 rating

Confidence interval: 1,265.66 – 1,287.72

3105 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,262.85 rating

Confidence interval: 1,255.45 – 1,270.24

8131 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,281.86 rating

Confidence interval: 1,276.19 – 1,287.53

16478 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,273.89 rating

Confidence interval: 1,262.08 – 1,285.71

2432 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Qwen-Max (0919)
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-28 · rating

Qwen-Max (0919)

1,290.01 rating

Confidence interval: 1,251.43 – 1,328.58

222 votes

Oct 28, 2026

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