GeekRadar / The comparison desk

COMPARE.

AI models

alibaba

Qwen1.5-32B-Chat

Model evaluation

Capability & preference

Human preference · Arena

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

Qwen1.5-32B-Chat 1137.2 Qwen1.5-32B-Chat · 95% interval 1131.1–1143.2 · 21,741 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

Qwen1.5-32B-Chat

1,176.45 rating

Confidence interval: 1,163.11 – 1,189.80

3241 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,154.36 rating

Confidence interval: 1,143.49 – 1,165.22

3930 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,082.62 rating

Confidence interval: 1,070.35 – 1,094.89

3022 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,159.82 rating

Confidence interval: 1,152.17 – 1,167.47

11877 votes

Oct 28, 2026

Category: english
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

988.68 rating

Confidence interval: 979.30 – 998.05

14160 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,126.10 rating

Confidence interval: 1,107.99 – 1,144.20

1176 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,101.08 rating

Confidence interval: 1,065.77 – 1,136.40

313 votes

Oct 28, 2026

Category: french
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,058.28 rating

Confidence interval: 1,035.43 – 1,081.14

777 votes

Oct 28, 2026

Category: german
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,130.35 rating

Confidence interval: 1,121.11 – 1,139.59

6072 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,146.54 rating

Confidence interval: 1,135.53 – 1,157.55

3830 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,094.19 rating

Confidence interval: 1,080.56 – 1,107.82

2307 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,080.44 rating

Confidence interval: 1,068.37 – 1,092.52

3063 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,140.53 rating

Confidence interval: 1,122.54 – 1,158.52

1227 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,132.16 rating

Confidence interval: 1,120.69 – 1,143.63

3861 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,162.56 rating

Confidence interval: 1,150.04 – 1,175.08

2405 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,110.82 rating

Confidence interval: 1,092.32 – 1,129.33

1187 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,146.46 rating

Confidence interval: 1,137.04 – 1,155.88

6351 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,118.10 rating

Confidence interval: 1,107.89 – 1,128.31

5401 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,115.41 rating

Confidence interval: 1,106.89 – 1,123.94

7653 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,027.30 rating

Confidence interval: 993.50 – 1,061.09

324 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,007.59 rating

Confidence interval: 976.03 – 1,039.16

395 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,145.69 rating

Confidence interval: 1,133.17 – 1,158.20

2574 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,155.07 rating

Confidence interval: 1,143.38 – 1,166.75

2649 votes

Oct 28, 2026

Category: math
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,139.70 rating

Confidence interval: 1,127.36 – 1,152.04

3140 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,106.25 rating

Confidence interval: 1,098.20 – 1,114.31

9864 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,137.18 rating

Confidence interval: 1,131.11 – 1,143.25

21741 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,072.66 rating

Confidence interval: 1,059.03 – 1,086.29

2175 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

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

Qwen1.5-32B-Chat

1,088.97 rating

Confidence interval: 1,057.22 – 1,120.72

369 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Qwen1.5-32B-Chat
Evaluation type: human preference

Run it locally

Inference · memory estimate

Qwen1.5-32B-Chat

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Qianwen LICENSE