Qwen3 VL 235B A22B Thinking
Stored tensors can include buffers and repeated shared weights. A verified unique parameter count is unavailable. Checkpoint size is not the memory required to run the model.
GeekRadar / The comparison desk
COMPARE.
AI modelsQwen3 VL 235B A22B Thinking
AI model Released
- Context window
- 131,072 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 VL 235B A22B Thinking
1,441.31 rating
Confidence interval: 1,413.64 – 1,468.98
443 votes
- Category
- chinese
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,425.00 rating
Confidence interval: 1,410.73 – 1,439.26
1638 votes
- Category
- coding
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,343.58 rating
Confidence interval: 1,325.43 – 1,361.74
1021 votes
- Category
- creative_writing
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,419.90 rating
Confidence interval: 1,410.06 – 1,429.74
3495 votes
- Category
- english
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,378.81 rating
Confidence interval: 1,369.22 – 1,388.39
5534 votes
- Category
- exclude_ties
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,428.95 rating
Confidence interval: 1,400.08 – 1,457.82
412 votes
- Category
- expert
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,417.10 rating
Confidence interval: 1,373.83 – 1,460.37
179 votes
- Category
- german
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,406.91 rating
Confidence interval: 1,397.77 – 1,416.05
4047 votes
- Category
- hard_prompts
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,417.07 rating
Confidence interval: 1,403.55 – 1,430.58
1833 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,391.02 rating
Confidence interval: 1,376.57 – 1,405.47
1572 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,369.50 rating
Confidence interval: 1,354.32 – 1,384.69
1446 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,407.39 rating
Confidence interval: 1,382.14 – 1,432.64
494 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,412.40 rating
Confidence interval: 1,395.73 – 1,429.07
1241 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,433.67 rating
Confidence interval: 1,405.16 – 1,462.19
389 votes
- Category
- industry_mathematical
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,414.86 rating
Confidence interval: 1,386.97 – 1,442.75
439 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,425.22 rating
Confidence interval: 1,414.30 – 1,436.15
2787 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,364.21 rating
Confidence interval: 1,350.23 – 1,378.18
1755 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,374.31 rating
Confidence interval: 1,362.05 – 1,386.58
2158 votes
- Category
- instruction_following
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,357.88 rating
Confidence interval: 1,319.45 – 1,396.30
239 votes
- Category
- korean
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,390.77 rating
Confidence interval: 1,377.20 – 1,404.35
1767 votes
- Category
- longer_query
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,409.54 rating
Confidence interval: 1,381.24 – 1,437.84
424 votes
- Category
- math
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,387.41 rating
Confidence interval: 1,370.79 – 1,404.02
1256 votes
- Category
- multi_turn
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,376.60 rating
Confidence interval: 1,367.81 – 1,385.39
4367 votes
- Category
- non_english
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,400.49 rating
Confidence interval: 1,393.67 – 1,407.31
7862 votes
- Category
- overall
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,365.54 rating
Confidence interval: 1,338.01 – 1,393.06
399 votes
- Category
- polish
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,369.62 rating
Confidence interval: 1,347.21 – 1,392.04
618 votes
- Category
- russian
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Thinking
1,401.86 rating
Confidence interval: 1,370.85 – 1,432.88
380 votes
- Category
- spanish
- Evaluated configuration
- Qwen3-VL-235B-A22B-Thinking
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,441.58 rating
Confidence interval: 1,413.96 – 1,469.19
444 votes
- Category
- chinese
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,425.34 rating
Confidence interval: 1,411.09 – 1,439.60
1640 votes
- Category
- coding
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,343.88 rating
Confidence interval: 1,325.71 – 1,362.05
1018 votes
- Category
- creative_writing
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,420.06 rating
Confidence interval: 1,410.22 – 1,429.91
3494 votes
- Category
- english
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,379.18 rating
Confidence interval: 1,369.59 – 1,388.76
5532 votes
- Category
- exclude_ties
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,428.98 rating
Confidence interval: 1,400.10 – 1,457.85
412 votes
- Category
- expert
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,417.08 rating
Confidence interval: 1,373.81 – 1,460.35
179 votes
- Category
- german
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,407.25 rating
Confidence interval: 1,398.10 – 1,416.40
4043 votes
- Category
- hard_prompts
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,417.17 rating
Confidence interval: 1,403.65 – 1,430.69
1832 votes
- Category
- hard_prompts_english
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,391.53 rating
Confidence interval: 1,377.08 – 1,405.98
1573 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,369.72 rating
Confidence interval: 1,354.54 – 1,384.91
1444 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,407.18 rating
Confidence interval: 1,381.92 – 1,432.43
494 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,412.44 rating
Confidence interval: 1,395.76 – 1,429.13
1240 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,434.86 rating
Confidence interval: 1,406.33 – 1,463.38
388 votes
- Category
- industry_mathematical
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,414.94 rating
Confidence interval: 1,387.05 – 1,442.84
439 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,425.46 rating
Confidence interval: 1,414.54 – 1,436.38
2789 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,364.58 rating
Confidence interval: 1,350.61 – 1,378.55
1754 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,375.01 rating
Confidence interval: 1,362.75 – 1,387.28
2156 votes
- Category
- instruction_following
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,358.01 rating
Confidence interval: 1,319.59 – 1,396.42
239 votes
- Category
- korean
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,390.68 rating
Confidence interval: 1,377.12 – 1,404.25
1768 votes
- Category
- longer_query
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,411.38 rating
Confidence interval: 1,383.03 – 1,439.72
422 votes
- Category
- math
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,387.61 rating
Confidence interval: 1,371.00 – 1,404.22
1257 votes
- Category
- multi_turn
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,376.96 rating
Confidence interval: 1,368.16 – 1,385.75
4365 votes
- Category
- non_english
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,400.73 rating
Confidence interval: 1,393.90 – 1,407.55
7859 votes
- Category
- overall
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,365.58 rating
Confidence interval: 1,338.05 – 1,393.10
399 votes
- Category
- polish
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,370.27 rating
Confidence interval: 1,347.90 – 1,392.63
620 votes
- Category
- russian
- Evaluated configuration
- qwen3-vl-235b-a22b-thinking
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Thinking
1,402.57 rating
Confidence interval: 1,371.51 – 1,433.64
379 votes
- Category
- spanish
- Evaluated configuration
- qwen3-vl-235b-a22b-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 VL 235B A22B Thinking
Capabilities
- Context window
- 131,072 tokens
- Maximum output
- 32,768 tokens
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Knowledge cutoff
- 2025-03-31
- Checkpoint tensor payload
- 438.97 GiB
Input modalities
- text
- image
Output modalities
- text
Processing & platform
- Architecture
- qwen3_vl_moe
0 selected Compare 0