Qwen3 235B-A22B Thinking 2507
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsQwen3 235B-A22B Thinking 2507
AI model Released
- Context window
- 262,144 tokens
- Maximum output
- 81,920 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 · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,480.91 rating
Confidence interval: 1,454.92 – 1,506.90
536 votes
- Category
- chinese
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,424.28 rating
Confidence interval: 1,409.58 – 1,438.98
1591 votes
- Category
- coding
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,383.56 rating
Confidence interval: 1,365.89 – 1,401.23
1084 votes
- Category
- creative_writing
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,429.29 rating
Confidence interval: 1,419.87 – 1,438.70
3901 votes
- Category
- english
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,401.50 rating
Confidence interval: 1,392.18 – 1,410.82
6208 votes
- Category
- exclude_ties
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,462.83 rating
Confidence interval: 1,434.71 – 1,490.95
423 votes
- Category
- expert
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,408.01 rating
Confidence interval: 1,368.38 – 1,447.64
211 votes
- Category
- german
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,415.71 rating
Confidence interval: 1,406.25 – 1,425.17
3807 votes
- Category
- hard_prompts
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,431.25 rating
Confidence interval: 1,417.21 – 1,445.29
1717 votes
- Category
- hard_prompts_english
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,412.48 rating
Confidence interval: 1,397.46 – 1,427.51
1527 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,369.96 rating
Confidence interval: 1,355.34 – 1,384.59
1528 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,414.76 rating
Confidence interval: 1,390.22 – 1,439.30
532 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,432.66 rating
Confidence interval: 1,417.43 – 1,447.89
1495 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,435.07 rating
Confidence interval: 1,409.40 – 1,460.74
476 votes
- Category
- industry_mathematical
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,456.37 rating
Confidence interval: 1,430.49 – 1,482.24
509 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,430.85 rating
Confidence interval: 1,419.94 – 1,441.77
2910 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,387.70 rating
Confidence interval: 1,374.22 – 1,401.18
1860 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,386.00 rating
Confidence interval: 1,373.58 – 1,398.43
2094 votes
- Category
- instruction_following
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,386.37 rating
Confidence interval: 1,356.98 – 1,415.76
442 votes
- Category
- japanese
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,375.05 rating
Confidence interval: 1,334.08 – 1,416.02
204 votes
- Category
- korean
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,399.10 rating
Confidence interval: 1,384.94 – 1,413.25
1641 votes
- Category
- longer_query
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,412.21 rating
Confidence interval: 1,387.56 – 1,436.87
479 votes
- Category
- math
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,406.44 rating
Confidence interval: 1,390.76 – 1,422.12
1357 votes
- Category
- multi_turn
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,397.26 rating
Confidence interval: 1,388.89 – 1,405.63
4914 votes
- Category
- non_english
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,415.04 rating
Confidence interval: 1,408.51 – 1,421.58
8823 votes
- Category
- overall
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,389.96 rating
Confidence interval: 1,369.34 – 1,410.58
783 votes
- Category
- polish
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,399.94 rating
Confidence interval: 1,376.11 – 1,423.78
530 votes
- Category
- russian
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
Qwen3 235B-A22B Thinking 2507
1,388.56 rating
Confidence interval: 1,347.54 – 1,429.57
185 votes
- Category
- spanish
- Evaluated configuration
- qwen3-235b-a22b-thinking-2507
- 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 235B-A22B Thinking 2507
Capabilities
- Context window
- 262,144 tokens
- Maximum output
- 81,920 tokens
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- Yes
- Model license
- Apache 2.0
Input modalities
- text
Output modalities
- text
0 selected Compare 0