Qwen3 VL 235B A22B Instruct
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 Instruct
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 Instruct
1,461.85 rating
Confidence interval: 1,438.70 – 1,485.00
714 votes
- Category
- chinese
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,438.23 rating
Confidence interval: 1,425.30 – 1,451.16
2311 votes
- Category
- coding
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,365.60 rating
Confidence interval: 1,348.87 – 1,382.34
1357 votes
- Category
- creative_writing
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,429.29 rating
Confidence interval: 1,420.05 – 1,438.52
4932 votes
- Category
- english
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,407.13 rating
Confidence interval: 1,397.97 – 1,416.29
7988 votes
- Category
- exclude_ties
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,442.05 rating
Confidence interval: 1,418.00 – 1,466.09
596 votes
- Category
- expert
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,450.63 rating
Confidence interval: 1,410.73 – 1,490.52
261 votes
- Category
- french
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,424.20 rating
Confidence interval: 1,388.71 – 1,459.69
279 votes
- Category
- german
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,428.18 rating
Confidence interval: 1,419.60 – 1,436.75
5704 votes
- Category
- hard_prompts
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,439.23 rating
Confidence interval: 1,426.55 – 1,451.92
2499 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,432.87 rating
Confidence interval: 1,419.16 – 1,446.59
2226 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,368.24 rating
Confidence interval: 1,353.88 – 1,382.61
1889 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,438.55 rating
Confidence interval: 1,416.10 – 1,461.00
736 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,444.67 rating
Confidence interval: 1,429.48 – 1,459.87
1733 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,419.18 rating
Confidence interval: 1,395.39 – 1,442.96
600 votes
- Category
- industry_mathematical
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,430.56 rating
Confidence interval: 1,406.08 – 1,455.03
627 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,441.81 rating
Confidence interval: 1,431.74 – 1,451.88
4003 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,392.43 rating
Confidence interval: 1,379.53 – 1,405.32
2354 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,406.22 rating
Confidence interval: 1,394.97 – 1,417.47
2946 votes
- Category
- instruction_following
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,385.05 rating
Confidence interval: 1,340.09 – 1,430.02
170 votes
- Category
- japanese
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,394.16 rating
Confidence interval: 1,360.87 – 1,427.44
325 votes
- Category
- korean
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,419.59 rating
Confidence interval: 1,406.81 – 1,432.38
2250 votes
- Category
- longer_query
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,425.28 rating
Confidence interval: 1,402.61 – 1,447.95
699 votes
- Category
- math
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,427.95 rating
Confidence interval: 1,413.57 – 1,442.33
1929 votes
- Category
- multi_turn
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,404.49 rating
Confidence interval: 1,396.20 – 1,412.77
6382 votes
- Category
- non_english
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,420.04 rating
Confidence interval: 1,413.54 – 1,426.54
11314 votes
- Category
- overall
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,419.35 rating
Confidence interval: 1,392.87 – 1,445.83
540 votes
- Category
- polish
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,407.51 rating
Confidence interval: 1,387.35 – 1,427.68
882 votes
- Category
- russian
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
Qwen3 VL 235B A22B Instruct
1,428.14 rating
Confidence interval: 1,400.04 – 1,456.24
460 votes
- Category
- spanish
- Evaluated configuration
- Qwen3-VL-235B-A22B-Instruct
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,462.60 rating
Confidence interval: 1,439.44 – 1,485.77
714 votes
- Category
- chinese
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,438.50 rating
Confidence interval: 1,425.58 – 1,451.43
2313 votes
- Category
- coding
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,366.07 rating
Confidence interval: 1,349.33 – 1,382.80
1356 votes
- Category
- creative_writing
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,429.07 rating
Confidence interval: 1,419.83 – 1,438.30
4932 votes
- Category
- english
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,407.22 rating
Confidence interval: 1,398.06 – 1,416.38
7991 votes
- Category
- exclude_ties
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,442.08 rating
Confidence interval: 1,418.03 – 1,466.13
596 votes
- Category
- expert
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,451.71 rating
Confidence interval: 1,411.84 – 1,491.59
262 votes
- Category
- french
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,424.17 rating
Confidence interval: 1,388.68 – 1,459.65
279 votes
- Category
- german
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,428.28 rating
Confidence interval: 1,419.71 – 1,436.86
5706 votes
- Category
- hard_prompts
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,439.14 rating
Confidence interval: 1,426.45 – 1,451.82
2499 votes
- Category
- hard_prompts_english
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,432.98 rating
Confidence interval: 1,419.26 – 1,446.69
2226 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,368.22 rating
Confidence interval: 1,353.86 – 1,382.59
1889 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,438.34 rating
Confidence interval: 1,415.89 – 1,460.80
736 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,444.50 rating
Confidence interval: 1,429.32 – 1,459.68
1733 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,419.21 rating
Confidence interval: 1,395.42 – 1,443.00
600 votes
- Category
- industry_mathematical
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,430.66 rating
Confidence interval: 1,406.19 – 1,455.14
627 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,441.98 rating
Confidence interval: 1,431.91 – 1,452.05
4005 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,392.70 rating
Confidence interval: 1,379.80 – 1,405.59
2353 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,406.37 rating
Confidence interval: 1,395.12 – 1,417.62
2946 votes
- Category
- instruction_following
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,384.80 rating
Confidence interval: 1,339.83 – 1,429.77
170 votes
- Category
- japanese
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,394.21 rating
Confidence interval: 1,360.92 – 1,427.50
325 votes
- Category
- korean
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,419.90 rating
Confidence interval: 1,407.12 – 1,432.68
2250 votes
- Category
- longer_query
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,425.28 rating
Confidence interval: 1,402.65 – 1,447.92
700 votes
- Category
- math
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,427.98 rating
Confidence interval: 1,413.60 – 1,442.36
1929 votes
- Category
- multi_turn
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,404.81 rating
Confidence interval: 1,396.54 – 1,413.09
6388 votes
- Category
- non_english
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,420.09 rating
Confidence interval: 1,413.59 – 1,426.59
11320 votes
- Category
- overall
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,419.39 rating
Confidence interval: 1,392.91 – 1,445.87
540 votes
- Category
- polish
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,407.63 rating
Confidence interval: 1,387.49 – 1,427.76
883 votes
- Category
- russian
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
Qwen3 VL 235B A22B Instruct
1,428.04 rating
Confidence interval: 1,399.93 – 1,456.15
460 votes
- Category
- spanish
- Evaluated configuration
- qwen3-vl-235b-a22b-instruct
- 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 Instruct
Qwen3 VL 235B A22B Instruct / Pricing tiers
| Provider / scope | Rate | Currency | Amount / unit |
|---|---|---|---|
| DeepInfraQwen/Qwen3-VL-235B-A22B-InstructStandard | Cached input | USD | 0.11 / 1M tokens |
| Input | USD | 0.2 / 1M tokens | |
| Output | USD | 0.88 / 1M tokens |
Capabilities
- Context window
- 131,072 tokens
- Maximum output
- 32,768 tokens
- Reasoning
- No
- 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