GeekRadar / The comparison desk
COMPARE.
AI models
alibaba

qwq-32b-preview

Model evaluation

Capability & preference

Human preference · Arena

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

qwq-32b-preview 1161.8 qwq-32b-preview · 95% interval 1150.4–1173.1 · 3,231 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

qwq-32b-preview

1,217.83 rating

Confidence interval: 1,177.56 – 1,258.11

206 votes

Category
chinese
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

qwq-32b-preview

1,155.04 rating

Confidence interval: 1,131.33 – 1,178.75

566 votes

Category
coding
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

qwq-32b-preview

1,133.59 rating

Confidence interval: 1,105.42 – 1,161.77

454 votes

Category
creative_writing
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

qwq-32b-preview

1,184.22 rating

Confidence interval: 1,169.73 – 1,198.71

1783 votes

Category
english
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

qwq-32b-preview

1,022.41 rating

Confidence interval: 1,004.31 – 1,040.51

2230 votes

Category
exclude_ties
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

qwq-32b-preview

1,134.32 rating

Confidence interval: 1,098.62 – 1,170.02

232 votes

Category
expert
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

qwq-32b-preview

1,162.42 rating

Confidence interval: 1,143.33 – 1,181.50

852 votes

Category
hard_prompts
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

qwq-32b-preview

1,170.78 rating

Confidence interval: 1,146.35 – 1,195.21

519 votes

Category
hard_prompts_english
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

qwq-32b-preview

1,098.33 rating

Confidence interval: 1,066.87 – 1,129.78

374 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

qwq-32b-preview

1,114.52 rating

Confidence interval: 1,088.52 – 1,140.53

540 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

qwq-32b-preview

1,142.85 rating

Confidence interval: 1,102.04 – 1,183.66

214 votes

Category
industry_legal_and_government
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

qwq-32b-preview

1,153.87 rating

Confidence interval: 1,128.84 – 1,178.91

583 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

qwq-32b-preview

1,221.42 rating

Confidence interval: 1,195.00 – 1,247.84

422 votes

Category
industry_mathematical
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

qwq-32b-preview

1,154.17 rating

Confidence interval: 1,133.90 – 1,174.44

824 votes

Category
industry_software_and_it_services
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

qwq-32b-preview

1,139.43 rating

Confidence interval: 1,118.87 – 1,159.99

855 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

qwq-32b-preview

1,155.78 rating

Confidence interval: 1,139.95 – 1,171.60

1329 votes

Category
instruction_following
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

qwq-32b-preview

1,166.50 rating

Confidence interval: 1,140.70 – 1,192.31

475 votes

Category
longer_query
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

qwq-32b-preview

1,213.42 rating

Confidence interval: 1,189.10 – 1,237.74

480 votes

Category
math
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

qwq-32b-preview

1,140.66 rating

Confidence interval: 1,113.76 – 1,167.55

487 votes

Category
multi_turn
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

qwq-32b-preview

1,129.55 rating

Confidence interval: 1,113.95 – 1,145.15

1448 votes

Category
non_english
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

qwq-32b-preview

1,161.75 rating

Confidence interval: 1,150.42 – 1,173.08

3231 votes

Category
overall
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

qwq-32b-preview

1,114.53 rating

Confidence interval: 1,088.45 – 1,140.60

527 votes

Category
russian
Evaluated configuration
qwq-32b-preview
Evaluation type
human preference

Run it locally

Inference · memory estimate

qwq-32b-preview

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Apache 2.0