GeekRadar / The comparison desk
COMPARE.
AI models
alibaba

Qwen3-30B-A3B-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.

Qwen3-30B-A3B-Instruct (2507) 1383.8 Qwen3-30B-A3B-Instruct (2507) · 95% interval 1378.9–1388.7 · 23,312 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

Qwen3-30B-A3B-Instruct (2507)

1,432.35 rating

Confidence interval: 1,417.97 – 1,446.73

1752 votes

Category
chinese
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,415.98 rating

Confidence interval: 1,407.17 – 1,424.78

4612 votes

Category
coding
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,316.92 rating

Confidence interval: 1,306.00 – 1,327.84

2965 votes

Category
creative_writing
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,391.20 rating

Confidence interval: 1,384.66 – 1,397.75

9758 votes

Category
english
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,357.79 rating

Confidence interval: 1,351.11 – 1,364.48

16354 votes

Category
exclude_ties
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,396.56 rating

Confidence interval: 1,379.90 – 1,413.22

1174 votes

Category
expert
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,418.37 rating

Confidence interval: 1,386.43 – 1,450.31

337 votes

Category
french
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,378.84 rating

Confidence interval: 1,353.11 – 1,404.57

523 votes

Category
german
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,397.81 rating

Confidence interval: 1,391.54 – 1,404.09

10973 votes

Category
hard_prompts
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,406.55 rating

Confidence interval: 1,397.84 – 1,415.25

4748 votes

Category
hard_prompts_english
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,389.08 rating

Confidence interval: 1,379.72 – 1,398.43

4116 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,334.54 rating

Confidence interval: 1,325.41 – 1,343.67

4126 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,386.74 rating

Confidence interval: 1,371.37 – 1,402.12

1463 votes

Category
industry_legal_and_government
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,392.83 rating

Confidence interval: 1,383.04 – 1,402.62

3675 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,411.13 rating

Confidence interval: 1,394.68 – 1,427.57

1209 votes

Category
industry_mathematical
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,392.23 rating

Confidence interval: 1,375.87 – 1,408.59

1327 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,416.67 rating

Confidence interval: 1,409.57 – 1,423.76

7955 votes

Category
industry_software_and_it_services
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,335.72 rating

Confidence interval: 1,327.26 – 1,344.18

5073 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,362.92 rating

Confidence interval: 1,355.08 – 1,370.75

5970 votes

Category
instruction_following
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,337.58 rating

Confidence interval: 1,315.47 – 1,359.69

766 votes

Category
japanese
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,330.99 rating

Confidence interval: 1,306.13 – 1,355.85

592 votes

Category
korean
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,378.34 rating

Confidence interval: 1,369.82 – 1,386.86

4942 votes

Category
longer_query
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,394.30 rating

Confidence interval: 1,379.17 – 1,409.43

1394 votes

Category
math
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,378.46 rating

Confidence interval: 1,368.92 – 1,388.00

3931 votes

Category
multi_turn
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,371.51 rating

Confidence interval: 1,365.66 – 1,377.37

13546 votes

Category
non_english
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,383.78 rating

Confidence interval: 1,378.90 – 1,388.66

23312 votes

Category
overall
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,353.14 rating

Confidence interval: 1,337.94 – 1,368.35

1541 votes

Category
polish
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,369.24 rating

Confidence interval: 1,354.94 – 1,383.53

1563 votes

Category
russian
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Qwen3-30B-A3B-Instruct (2507)

1,403.54 rating

Confidence interval: 1,381.20 – 1,425.89

715 votes

Category
spanish
Evaluated configuration
Qwen3-30B-A3B-Instruct (2507)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Qwen3-30B-A3B-Instruct (2507)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Apache 2.0