Qwen3-Next 80B-A3B (Thinking)
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsQwen3-Next 80B-A3B (Thinking)
AI model
- Context window
- 262,144 tokens
- Maximum output
- 32,768 tokens
- Open weights
- Yes
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-Next 80B-A3B (Thinking)
1,406.34 rating
Confidence interval: 1,388.48 – 1,424.20
1059 votes
- Category
- chinese
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,391.28 rating
Confidence interval: 1,379.84 – 1,402.73
2666 votes
- Category
- coding
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,313.98 rating
Confidence interval: 1,299.87 – 1,328.09
1776 votes
- Category
- creative_writing
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,392.19 rating
Confidence interval: 1,384.26 – 1,400.12
5903 votes
- Category
- english
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,333.86 rating
Confidence interval: 1,325.92 – 1,341.81
9586 votes
- Category
- exclude_ties
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,375.05 rating
Confidence interval: 1,352.25 – 1,397.85
662 votes
- Category
- expert
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,351.49 rating
Confidence interval: 1,312.06 – 1,390.91
218 votes
- Category
- french
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,355.96 rating
Confidence interval: 1,322.79 – 1,389.12
296 votes
- Category
- german
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,371.15 rating
Confidence interval: 1,363.63 – 1,378.67
6664 votes
- Category
- hard_prompts
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,383.98 rating
Confidence interval: 1,373.27 – 1,394.68
3016 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,359.87 rating
Confidence interval: 1,348.08 – 1,371.65
2490 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,312.25 rating
Confidence interval: 1,300.41 – 1,324.08
2445 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,364.33 rating
Confidence interval: 1,344.13 – 1,384.52
841 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,384.20 rating
Confidence interval: 1,371.43 – 1,396.97
2104 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,389.54 rating
Confidence interval: 1,367.34 – 1,411.74
686 votes
- Category
- industry_mathematical
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,391.94 rating
Confidence interval: 1,369.69 – 1,414.20
708 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,393.21 rating
Confidence interval: 1,384.49 – 1,401.92
4734 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,330.11 rating
Confidence interval: 1,319.45 – 1,340.76
3065 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,343.14 rating
Confidence interval: 1,333.28 – 1,353.00
3533 votes
- Category
- instruction_following
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,280.35 rating
Confidence interval: 1,239.16 – 1,321.55
206 votes
- Category
- japanese
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,309.15 rating
Confidence interval: 1,276.84 – 1,341.45
357 votes
- Category
- korean
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,352.66 rating
Confidence interval: 1,341.74 – 1,363.59
2883 votes
- Category
- longer_query
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,397.87 rating
Confidence interval: 1,378.14 – 1,417.59
822 votes
- Category
- math
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,345.98 rating
Confidence interval: 1,333.20 – 1,358.75
2218 votes
- Category
- multi_turn
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,342.31 rating
Confidence interval: 1,335.19 – 1,349.44
7573 votes
- Category
- non_english
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,368.06 rating
Confidence interval: 1,362.22 – 1,373.91
13476 votes
- Category
- overall
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,344.94 rating
Confidence interval: 1,322.76 – 1,367.13
709 votes
- Category
- polish
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,337.22 rating
Confidence interval: 1,318.94 – 1,355.51
928 votes
- Category
- russian
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
Qwen3-Next 80B-A3B (Thinking)
1,359.27 rating
Confidence interval: 1,331.26 – 1,387.28
458 votes
- Category
- spanish
- Evaluated configuration
- Qwen3-Next-80B-A3B-Thinking
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,406.82 rating
Confidence interval: 1,388.96 – 1,424.68
1060 votes
- Category
- chinese
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,391.52 rating
Confidence interval: 1,380.08 – 1,402.96
2667 votes
- Category
- coding
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,314.53 rating
Confidence interval: 1,300.42 – 1,328.64
1775 votes
- Category
- creative_writing
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,392.24 rating
Confidence interval: 1,384.32 – 1,400.17
5903 votes
- Category
- english
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,333.96 rating
Confidence interval: 1,326.02 – 1,341.90
9582 votes
- Category
- exclude_ties
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,375.97 rating
Confidence interval: 1,353.13 – 1,398.81
660 votes
- Category
- expert
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,352.63 rating
Confidence interval: 1,313.17 – 1,392.09
217 votes
- Category
- french
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,357.17 rating
Confidence interval: 1,324.01 – 1,390.33
295 votes
- Category
- german
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,371.32 rating
Confidence interval: 1,363.80 – 1,378.84
6662 votes
- Category
- hard_prompts
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,384.06 rating
Confidence interval: 1,373.36 – 1,394.77
3016 votes
- Category
- hard_prompts_english
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,359.95 rating
Confidence interval: 1,348.16 – 1,371.74
2490 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,312.46 rating
Confidence interval: 1,300.63 – 1,324.29
2445 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,363.80 rating
Confidence interval: 1,343.58 – 1,384.01
840 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,384.29 rating
Confidence interval: 1,371.51 – 1,397.06
2102 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,389.65 rating
Confidence interval: 1,367.48 – 1,411.83
688 votes
- Category
- industry_mathematical
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,392.05 rating
Confidence interval: 1,369.79 – 1,414.30
708 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,393.42 rating
Confidence interval: 1,384.71 – 1,402.13
4736 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,330.37 rating
Confidence interval: 1,319.71 – 1,341.03
3064 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,343.34 rating
Confidence interval: 1,333.48 – 1,353.19
3533 votes
- Category
- instruction_following
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,280.20 rating
Confidence interval: 1,239.00 – 1,321.39
206 votes
- Category
- japanese
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,310.18 rating
Confidence interval: 1,277.83 – 1,342.52
356 votes
- Category
- korean
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,352.84 rating
Confidence interval: 1,341.91 – 1,363.77
2881 votes
- Category
- longer_query
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,398.35 rating
Confidence interval: 1,378.63 – 1,418.08
823 votes
- Category
- math
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,346.48 rating
Confidence interval: 1,333.69 – 1,359.26
2217 votes
- Category
- multi_turn
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,342.48 rating
Confidence interval: 1,335.35 – 1,349.60
7571 votes
- Category
- non_english
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,368.09 rating
Confidence interval: 1,362.25 – 1,373.93
13474 votes
- Category
- overall
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,344.96 rating
Confidence interval: 1,322.78 – 1,367.15
709 votes
- Category
- polish
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,337.33 rating
Confidence interval: 1,319.07 – 1,355.59
929 votes
- Category
- russian
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
Qwen3-Next 80B-A3B (Thinking)
1,357.59 rating
Confidence interval: 1,329.53 – 1,385.65
456 votes
- Category
- spanish
- Evaluated configuration
- qwen3-next-80b-a3b-thinking
- 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-Next 80B-A3B (Thinking)
Capabilities
- Context window
- 262,144 tokens
- Maximum output
- 32,768 tokens
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Knowledge cutoff
- 2025-04
- Model license
- Apache 2.0
Input modalities
- text
Output modalities
- text
0 selected Compare 0