Qwen3.8 Max
Closed weights. No supported local deployment or GPU requirement is published.
GeekRadar / The comparison desk
COMPARE.
AI modelsQwen3.8 Max
AI model Released
- Context window
- 1,000,000 tokens
- Maximum output
- 131,072 tokens
- Open weights
- No
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 · 2026-10-28 · rating
Qwen3.8 Max
1,540.00 rating
Confidence interval: 1,527.39 – 1,552.62
2425 votes
- Category
- chinese
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,503.50 rating
Confidence interval: 1,496.33 – 1,510.68
8708 votes
- Category
- coding
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,478.42 rating
Confidence interval: 1,469.96 – 1,486.89
6348 votes
- Category
- creative_writing
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,492.77 rating
Confidence interval: 1,486.44 – 1,499.09
12039 votes
- Category
- english
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,494.24 rating
Confidence interval: 1,488.13 – 1,500.35
23485 votes
- Category
- exclude_ties
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,507.54 rating
Confidence interval: 1,497.26 – 1,517.81
3496 votes
- Category
- expert
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,502.97 rating
Confidence interval: 1,484.48 – 1,521.46
1157 votes
- Category
- french
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,475.32 rating
Confidence interval: 1,449.70 – 1,500.94
500 votes
- Category
- german
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,496.36 rating
Confidence interval: 1,490.94 – 1,501.79
20978 votes
- Category
- hard_prompts
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,504.73 rating
Confidence interval: 1,497.34 – 1,512.13
8011 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,480.46 rating
Confidence interval: 1,472.11 – 1,488.82
5844 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,465.07 rating
Confidence interval: 1,457.46 – 1,472.68
7969 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,493.76 rating
Confidence interval: 1,481.05 – 1,506.46
2352 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,513.63 rating
Confidence interval: 1,504.68 – 1,522.58
4948 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,495.96 rating
Confidence interval: 1,482.06 – 1,509.87
1887 votes
- Category
- industry_mathematical
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,504.66 rating
Confidence interval: 1,491.07 – 1,518.26
2113 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,498.51 rating
Confidence interval: 1,492.24 – 1,504.79
12546 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,477.56 rating
Confidence interval: 1,470.11 – 1,485.01
8363 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,480.43 rating
Confidence interval: 1,473.86 – 1,487.01
11282 votes
- Category
- instruction_following
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,471.49 rating
Confidence interval: 1,444.68 – 1,498.30
581 votes
- Category
- japanese
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,462.26 rating
Confidence interval: 1,438.23 – 1,486.29
652 votes
- Category
- korean
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,488.47 rating
Confidence interval: 1,482.16 – 1,494.79
14028 votes
- Category
- longer_query
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,505.99 rating
Confidence interval: 1,491.17 – 1,520.81
1622 votes
- Category
- math
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,491.03 rating
Confidence interval: 1,481.87 – 1,500.18
4825 votes
- Category
- multi_turn
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,472.39 rating
Confidence interval: 1,466.94 – 1,477.84
19871 votes
- Category
- non_english
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,483.29 rating
Confidence interval: 1,478.52 – 1,488.06
31915 votes
- Category
- overall
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,475.31 rating
Confidence interval: 1,449.18 – 1,501.44
474 votes
- Category
- polish
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,483.55 rating
Confidence interval: 1,474.02 – 1,493.08
4278 votes
- Category
- russian
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
Qwen3.8 Max
1,488.06 rating
Confidence interval: 1,469.00 – 1,507.11
1026 votes
- Category
- spanish
- Evaluated configuration
- Qwen3.8-Max
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,535.98 rating
Confidence interval: 1,522.40 – 1,549.56
2058 votes
- Category
- chinese
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,501.93 rating
Confidence interval: 1,494.44 – 1,509.43
7677 votes
- Category
- coding
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,478.63 rating
Confidence interval: 1,469.70 – 1,487.55
5471 votes
- Category
- creative_writing
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,491.99 rating
Confidence interval: 1,485.40 – 1,498.57
10584 votes
- Category
- english
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,493.49 rating
Confidence interval: 1,487.11 – 1,499.88
20429 votes
- Category
- exclude_ties
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,507.10 rating
Confidence interval: 1,496.21 – 1,518.00
3086 votes
- Category
- expert
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,502.08 rating
Confidence interval: 1,482.21 – 1,521.95
969 votes
- Category
- french
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,483.17 rating
Confidence interval: 1,456.01 – 1,510.32
433 votes
- Category
- german
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,495.32 rating
Confidence interval: 1,489.69 – 1,500.95
18366 votes
- Category
- hard_prompts
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,503.71 rating
Confidence interval: 1,495.98 – 1,511.44
7058 votes
- Category
- hard_prompts_english
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,479.79 rating
Confidence interval: 1,471.06 – 1,488.51
5159 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,464.57 rating
Confidence interval: 1,456.60 – 1,472.53
6908 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,493.06 rating
Confidence interval: 1,479.57 – 1,506.55
2052 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,511.44 rating
Confidence interval: 1,502.00 – 1,520.88
4337 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,494.00 rating
Confidence interval: 1,479.23 – 1,508.76
1649 votes
- Category
- industry_mathematical
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,501.12 rating
Confidence interval: 1,486.73 – 1,515.51
1860 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,497.56 rating
Confidence interval: 1,491.03 – 1,504.10
11018 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,478.06 rating
Confidence interval: 1,470.28 – 1,485.84
7253 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,479.42 rating
Confidence interval: 1,472.57 – 1,486.27
9874 votes
- Category
- instruction_following
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,469.50 rating
Confidence interval: 1,440.75 – 1,498.24
505 votes
- Category
- japanese
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,463.65 rating
Confidence interval: 1,438.53 – 1,488.78
585 votes
- Category
- korean
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,488.36 rating
Confidence interval: 1,481.82 – 1,494.91
12332 votes
- Category
- longer_query
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,501.80 rating
Confidence interval: 1,485.94 – 1,517.66
1401 votes
- Category
- math
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,487.19 rating
Confidence interval: 1,477.58 – 1,496.80
4222 votes
- Category
- multi_turn
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,471.70 rating
Confidence interval: 1,466.02 – 1,477.38
17180 votes
- Category
- non_english
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,482.88 rating
Confidence interval: 1,477.93 – 1,487.83
27766 votes
- Category
- overall
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,472.38 rating
Confidence interval: 1,444.89 – 1,499.87
408 votes
- Category
- polish
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,481.71 rating
Confidence interval: 1,471.55 – 1,491.87
3656 votes
- Category
- russian
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
Qwen3.8 Max
1,491.70 rating
Confidence interval: 1,471.11 – 1,512.30
875 votes
- Category
- spanish
- Evaluated configuration
- qwen3.8-max
- Evaluation type
- human preference
Run it locally
API cost
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.
Qwen3.8 Max
Qwen3.8 Max / Pricing tiers
| Provider / scope | Rate | Currency | Amount / unit |
|---|---|---|---|
| DeepInfraQwen/Qwen3.8-MaxStandard | Cached input | USD | 0.206 / 1M tokens |
| Input | USD | 1.65 / 1M tokens | |
| Output | USD | 4.951 / 1M tokens |
Capabilities
- Context window
- 1,000,000 tokens
- Maximum output
- 131,072 tokens
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- No
- Model license
- Proprietary
Input modalities
- text
- image
- video
Output modalities
- text
0 selected Compare 0