GeekRadar / The comparison desk
COMPARE.
AI models
alibaba

qwen3-235b-a22b-no-thinking

Model evaluation

Capability & preference

Human preference · Arena

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

qwen3-235b-a22b-no-thinking 1393.4 qwen3-235b-a22b-no-thinking · 95% interval 1388.9–1397.9 · 37,484 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

qwen3-235b-a22b-no-thinking

1,424.31 rating

Confidence interval: 1,412.33 – 1,436.29

2575 votes

Category
chinese
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,397.51 rating

Confidence interval: 1,389.99 – 1,405.03

6915 votes

Category
coding
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,356.23 rating

Confidence interval: 1,347.19 – 1,365.27

4565 votes

Category
creative_writing
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,396.41 rating

Confidence interval: 1,390.80 – 1,402.03

16621 votes

Category
english
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,370.51 rating

Confidence interval: 1,364.49 – 1,376.52

26660 votes

Category
exclude_ties
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,368.96 rating

Confidence interval: 1,355.42 – 1,382.50

1912 votes

Category
expert
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,368.03 rating

Confidence interval: 1,341.94 – 1,394.11

530 votes

Category
french
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,381.77 rating

Confidence interval: 1,363.42 – 1,400.13

1079 votes

Category
german
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,393.09 rating

Confidence interval: 1,387.46 – 1,398.73

16392 votes

Category
hard_prompts
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,392.01 rating

Confidence interval: 1,384.62 – 1,399.40

7385 votes

Category
hard_prompts_english
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,392.07 rating

Confidence interval: 1,384.03 – 1,400.10

6280 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,348.95 rating

Confidence interval: 1,341.33 – 1,356.57

6604 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,393.92 rating

Confidence interval: 1,382.03 – 1,405.81

2517 votes

Category
industry_legal_and_government
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,405.60 rating

Confidence interval: 1,397.44 – 1,413.76

6252 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,401.32 rating

Confidence interval: 1,389.03 – 1,413.60

2281 votes

Category
industry_mathematical
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,407.61 rating

Confidence interval: 1,394.84 – 1,420.37

2318 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,408.62 rating

Confidence interval: 1,402.48 – 1,414.77

12409 votes

Category
industry_software_and_it_services
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,366.30 rating

Confidence interval: 1,359.16 – 1,373.45

8001 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,361.59 rating

Confidence interval: 1,354.81 – 1,368.37

9219 votes

Category
instruction_following
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,371.65 rating

Confidence interval: 1,351.29 – 1,392.01

885 votes

Category
japanese
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,358.47 rating

Confidence interval: 1,335.52 – 1,381.43

740 votes

Category
korean
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,388.71 rating

Confidence interval: 1,381.25 – 1,396.17

7151 votes

Category
longer_query
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,396.89 rating

Confidence interval: 1,384.93 – 1,408.85

2379 votes

Category
math
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,398.09 rating

Confidence interval: 1,390.18 – 1,405.99

6543 votes

Category
multi_turn
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,384.13 rating

Confidence interval: 1,378.83 – 1,389.43

20859 votes

Category
non_english
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,393.39 rating

Confidence interval: 1,388.89 – 1,397.89

37484 votes

Category
overall
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,385.38 rating

Confidence interval: 1,374.38 – 1,396.38

3629 votes

Category
polish
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,394.10 rating

Confidence interval: 1,383.37 – 1,404.84

2911 votes

Category
russian
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

qwen3-235b-a22b-no-thinking

1,402.69 rating

Confidence interval: 1,380.89 – 1,424.50

763 votes

Category
spanish
Evaluated configuration
qwen3-235b-a22b-no-thinking
Evaluation type
human preference

Run it locally

Inference · memory estimate

qwen3-235b-a22b-no-thinking

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Apache 2.0