GeekRadar / The comparison desk

COMPARE.

AI models

alibaba

Qwen3.5-Max-Preview

Model evaluation

Capability & preference

Human preference · Arena

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

Qwen3.5-Max-Preview 1470.4 Qwen3.5-Max-Preview · 95% interval 1465.5–1475.2 · 22,582 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

Qwen3.5-Max-Preview

1,533.85 rating

Confidence interval: 1,518.58 – 1,549.12

1594 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,486.77 rating

Confidence interval: 1,478.91 – 1,494.63

6356 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,463.71 rating

Confidence interval: 1,453.00 – 1,474.42

3319 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,475.35 rating

Confidence interval: 1,468.89 – 1,481.81

10155 votes

Oct 28, 2026

Category: english
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,478.52 rating

Confidence interval: 1,472.02 – 1,485.02

16532 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,488.93 rating

Confidence interval: 1,476.17 – 1,501.69

2227 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,484.44 rating

Confidence interval: 1,462.24 – 1,506.63

749 votes

Oct 28, 2026

Category: french
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,487.46 rating

Confidence interval: 1,457.55 – 1,517.37

383 votes

Oct 28, 2026

Category: german
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,482.74 rating

Confidence interval: 1,476.97 – 1,488.51

14519 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,481.92 rating

Confidence interval: 1,474.22 – 1,489.63

6710 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,462.73 rating

Confidence interval: 1,453.64 – 1,471.82

4508 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,455.54 rating

Confidence interval: 1,446.06 – 1,465.01

4282 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,483.66 rating

Confidence interval: 1,469.49 – 1,497.84

1743 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,497.58 rating

Confidence interval: 1,487.69 – 1,507.48

3730 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,490.02 rating

Confidence interval: 1,473.54 – 1,506.49

1324 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,497.83 rating

Confidence interval: 1,483.01 – 1,512.66

1648 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,485.96 rating

Confidence interval: 1,479.19 – 1,492.74

8991 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,465.94 rating

Confidence interval: 1,457.32 – 1,474.57

5172 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,466.81 rating

Confidence interval: 1,459.42 – 1,474.20

7391 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,494.86 rating

Confidence interval: 1,450.66 – 1,539.06

209 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,437.84 rating

Confidence interval: 1,408.94 – 1,466.75

411 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,476.41 rating

Confidence interval: 1,469.35 – 1,483.48

8947 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,474.01 rating

Confidence interval: 1,458.32 – 1,489.71

1426 votes

Oct 28, 2026

Category: math
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,477.75 rating

Confidence interval: 1,467.85 – 1,487.65

3825 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,465.38 rating

Confidence interval: 1,459.41 – 1,471.35

12427 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,470.39 rating

Confidence interval: 1,465.54 – 1,475.25

22582 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,454.13 rating

Confidence interval: 1,428.55 – 1,479.71

486 votes

Oct 28, 2026

Category: polish
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,471.54 rating

Confidence interval: 1,459.82 – 1,483.26

2610 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-28 · rating

Qwen3.5-Max-Preview

1,469.92 rating

Confidence interval: 1,449.01 – 1,490.83

807 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Qwen3.5-Max-Preview
Evaluation type: human preference

Run it locally

Inference · memory estimate

Qwen3.5-Max-Preview

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Proprietary