GeekRadar / The comparison desk
COMPARE.
AI models
alibaba

Qwen3-235B-A22B-Instruct (2507)

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-Instruct (2507) 1419.3 Qwen3-235B-A22B-Instruct (2507) · 95% interval 1416.7–1421.8 · 98,029 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-Instruct (2507)

1,464.30 rating

Confidence interval: 1,457.07 – 1,471.54

7299 votes

Category
chinese
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,444.52 rating

Confidence interval: 1,440.04 – 1,448.99

21727 votes

Category
coding
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,374.88 rating

Confidence interval: 1,369.50 – 1,380.27

13872 votes

Category
creative_writing
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,423.99 rating

Confidence interval: 1,420.49 – 1,427.50

41006 votes

Category
english
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,407.80 rating

Confidence interval: 1,404.28 – 1,411.33

69779 votes

Category
exclude_ties
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,441.54 rating

Confidence interval: 1,434.04 – 1,449.04

6445 votes

Category
expert
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,444.64 rating

Confidence interval: 1,431.17 – 1,458.12

2161 votes

Category
french
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,432.45 rating

Confidence interval: 1,418.28 – 1,446.61

1811 votes

Category
german
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,433.37 rating

Confidence interval: 1,430.12 – 1,436.61

53492 votes

Category
hard_prompts
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,436.19 rating

Confidence interval: 1,431.78 – 1,440.60

22707 votes

Category
hard_prompts_english
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,418.11 rating

Confidence interval: 1,413.29 – 1,422.94

18244 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,374.25 rating

Confidence interval: 1,369.46 – 1,379.05

18037 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,428.65 rating

Confidence interval: 1,421.16 – 1,436.13

6598 votes

Category
industry_legal_and_government
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,437.35 rating

Confidence interval: 1,432.26 – 1,442.43

15738 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,441.07 rating

Confidence interval: 1,432.79 – 1,449.35

5202 votes

Category
industry_mathematical
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,445.17 rating

Confidence interval: 1,437.23 – 1,453.10

5914 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,446.53 rating

Confidence interval: 1,442.78 – 1,450.29

34877 votes

Category
industry_software_and_it_services
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,390.11 rating

Confidence interval: 1,385.68 – 1,394.53

22123 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,407.82 rating

Confidence interval: 1,403.77 – 1,411.87

27832 votes

Category
instruction_following
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,399.40 rating

Confidence interval: 1,383.20 – 1,415.59

1437 votes

Category
japanese
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,390.73 rating

Confidence interval: 1,375.94 – 1,405.52

1819 votes

Category
korean
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,426.07 rating

Confidence interval: 1,421.91 – 1,430.24

27093 votes

Category
longer_query
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,431.39 rating

Confidence interval: 1,423.75 – 1,439.03

6067 votes

Category
math
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,432.14 rating

Confidence interval: 1,427.15 – 1,437.14

17052 votes

Category
multi_turn
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,409.37 rating

Confidence interval: 1,406.23 – 1,412.52

56972 votes

Category
non_english
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,419.26 rating

Confidence interval: 1,416.72 – 1,421.79

98029 votes

Category
overall
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,406.74 rating

Confidence interval: 1,397.08 – 1,416.40

3937 votes

Category
polish
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,411.21 rating

Confidence interval: 1,405.23 – 1,417.20

10178 votes

Category
russian
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-11-06 · rating

Qwen3-235B-A22B-Instruct (2507)

1,429.50 rating

Confidence interval: 1,417.85 – 1,441.14

2912 votes

Category
spanish
Evaluated configuration
Qwen3-235B-A22B-Instruct (2507)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Qwen3-235B-A22B-Instruct (2507)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Apache 2.0