Qwen3-Max (2025-09-23)
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsQwen3-Max (2025-09-23)
Model evaluation
Capability & preference
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
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 · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,430.70 rating
Confidence interval: 1,405.76 – 1,455.63
502 votes
- Category
- chinese
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,438.75 rating
Confidence interval: 1,425.87 – 1,451.64
2025 votes
- Category
- coding
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,380.58 rating
Confidence interval: 1,363.53 – 1,397.63
1146 votes
- Category
- creative_writing
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,418.07 rating
Confidence interval: 1,408.87 – 1,427.26
3902 votes
- Category
- english
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,397.92 rating
Confidence interval: 1,388.82 – 1,407.02
6278 votes
- Category
- exclude_ties
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,398.00 rating
Confidence interval: 1,371.88 – 1,424.12
474 votes
- Category
- expert
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,437.04 rating
Confidence interval: 1,397.12 – 1,476.95
203 votes
- Category
- german
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,423.41 rating
Confidence interval: 1,414.95 – 1,431.86
4839 votes
- Category
- hard_prompts
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,429.09 rating
Confidence interval: 1,416.54 – 1,441.63
2121 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,394.46 rating
Confidence interval: 1,380.73 – 1,408.18
1752 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,379.07 rating
Confidence interval: 1,365.11 – 1,393.03
1657 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,399.51 rating
Confidence interval: 1,375.08 – 1,423.95
554 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,412.66 rating
Confidence interval: 1,397.40 – 1,427.92
1429 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,416.12 rating
Confidence interval: 1,390.22 – 1,442.01
479 votes
- Category
- industry_mathematical
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,405.71 rating
Confidence interval: 1,378.09 – 1,433.33
449 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,435.80 rating
Confidence interval: 1,425.72 – 1,445.88
3315 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,390.13 rating
Confidence interval: 1,377.19 – 1,403.08
1970 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,397.74 rating
Confidence interval: 1,386.50 – 1,408.97
2650 votes
- Category
- instruction_following
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,378.98 rating
Confidence interval: 1,342.32 – 1,415.64
262 votes
- Category
- korean
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,410.15 rating
Confidence interval: 1,397.50 – 1,422.80
2088 votes
- Category
- longer_query
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,436.02 rating
Confidence interval: 1,412.23 – 1,459.81
567 votes
- Category
- math
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,433.71 rating
Confidence interval: 1,419.04 – 1,448.38
1632 votes
- Category
- multi_turn
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,400.03 rating
Confidence interval: 1,391.78 – 1,408.29
5101 votes
- Category
- non_english
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,412.90 rating
Confidence interval: 1,406.44 – 1,419.36
9003 votes
- Category
- overall
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,393.76 rating
Confidence interval: 1,364.88 – 1,422.64
419 votes
- Category
- polish
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,416.35 rating
Confidence interval: 1,395.46 – 1,437.24
727 votes
- Category
- russian
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-11-08 · rating
Qwen3-Max (2025-09-23)
1,419.80 rating
Confidence interval: 1,391.38 – 1,448.21
438 votes
- Category
- spanish
- Evaluated configuration
- Qwen3-Max (2025-09-23)
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Proprietary
0 selected Compare 0