GeekRadar / The comparison desk
COMPARE.
AI models
alibaba

Qwen3-235B-A22B (Non-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 (Non-Thinking) 1393.5 Qwen3-235B-A22B (Non-Thinking) · 95% interval 1389.0–1398.0 · 37,464 votes · 2026-11-06

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 · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,424.31 rating

Confidence interval: 1,412.33 – 1,436.30

2574 votes

Category
chinese
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,397.48 rating

Confidence interval: 1,389.96 – 1,405.00

6911 votes

Category
coding
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,356.10 rating

Confidence interval: 1,347.05 – 1,365.14

4562 votes

Category
creative_writing
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,396.58 rating

Confidence interval: 1,390.96 – 1,402.20

16611 votes

Category
english
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,370.57 rating

Confidence interval: 1,364.55 – 1,376.58

26651 votes

Category
exclude_ties
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,368.97 rating

Confidence interval: 1,355.43 – 1,382.51

1914 votes

Category
expert
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,368.27 rating

Confidence interval: 1,342.19 – 1,394.35

530 votes

Category
french
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,382.24 rating

Confidence interval: 1,363.88 – 1,400.59

1080 votes

Category
german
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,393.06 rating

Confidence interval: 1,387.43 – 1,398.70

16386 votes

Category
hard_prompts
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,392.10 rating

Confidence interval: 1,384.71 – 1,399.50

7384 votes

Category
hard_prompts_english
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,391.84 rating

Confidence interval: 1,383.80 – 1,399.88

6278 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,349.15 rating

Confidence interval: 1,341.52 – 1,356.77

6604 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,394.17 rating

Confidence interval: 1,382.28 – 1,406.07

2516 votes

Category
industry_legal_and_government
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,405.55 rating

Confidence interval: 1,397.38 – 1,413.71

6251 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,401.55 rating

Confidence interval: 1,389.27 – 1,413.84

2282 votes

Category
industry_mathematical
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,407.62 rating

Confidence interval: 1,394.86 – 1,420.39

2319 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,408.61 rating

Confidence interval: 1,402.46 – 1,414.76

12399 votes

Category
industry_software_and_it_services
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,366.33 rating

Confidence interval: 1,359.18 – 1,373.48

7997 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,361.63 rating

Confidence interval: 1,354.85 – 1,368.41

9216 votes

Category
instruction_following
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,371.47 rating

Confidence interval: 1,351.06 – 1,391.87

884 votes

Category
japanese
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,358.73 rating

Confidence interval: 1,335.77 – 1,381.69

740 votes

Category
korean
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,388.78 rating

Confidence interval: 1,381.32 – 1,396.24

7152 votes

Category
longer_query
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,396.90 rating

Confidence interval: 1,384.93 – 1,408.86

2379 votes

Category
math
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,398.09 rating

Confidence interval: 1,390.18 – 1,406.00

6537 votes

Category
multi_turn
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,384.07 rating

Confidence interval: 1,378.76 – 1,389.37

20849 votes

Category
non_english
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,393.47 rating

Confidence interval: 1,388.97 – 1,397.97

37464 votes

Category
overall
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,385.52 rating

Confidence interval: 1,374.49 – 1,396.55

3627 votes

Category
polish
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,393.97 rating

Confidence interval: 1,383.22 – 1,404.72

2909 votes

Category
russian
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B (Non-Thinking)

1,402.79 rating

Confidence interval: 1,380.99 – 1,424.59

763 votes

Category
spanish
Evaluated configuration
Qwen3-235B-A22B (Non-Thinking)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Qwen3-235B-A22B (Non-Thinking)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Apache 2.0