deepseek-v3.2-thinking
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsdeepseek-v3.2-thinking
Model evaluation
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
deepseek-v3.2-thinking
1,447.79 rating
Confidence interval: 1,437.20 – 1,458.38
3129 votes
- Category
- chinese
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,453.40 rating
Confidence interval: 1,446.78 – 1,460.03
8890 votes
- Category
- coding
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,389.09 rating
Confidence interval: 1,381.44 – 1,396.74
6413 votes
- Category
- creative_writing
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,439.18 rating
Confidence interval: 1,434.10 – 1,444.27
17157 votes
- Category
- english
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,407.09 rating
Confidence interval: 1,402.09 – 1,412.09
29462 votes
- Category
- exclude_ties
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,430.97 rating
Confidence interval: 1,419.94 – 1,442.00
2886 votes
- Category
- expert
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,423.18 rating
Confidence interval: 1,404.36 – 1,441.99
1049 votes
- Category
- french
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,413.32 rating
Confidence interval: 1,392.24 – 1,434.40
748 votes
- Category
- german
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,430.57 rating
Confidence interval: 1,426.00 – 1,435.14
23348 votes
- Category
- hard_prompts
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,445.69 rating
Confidence interval: 1,439.26 – 1,452.11
9602 votes
- Category
- hard_prompts_english
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,409.29 rating
Confidence interval: 1,402.47 – 1,416.11
8103 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,386.65 rating
Confidence interval: 1,379.66 – 1,393.63
7759 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,418.65 rating
Confidence interval: 1,408.19 – 1,429.11
3086 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,425.95 rating
Confidence interval: 1,418.62 – 1,433.29
6871 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,439.84 rating
Confidence interval: 1,426.55 – 1,453.13
1967 votes
- Category
- industry_mathematical
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,420.70 rating
Confidence interval: 1,409.61 – 1,431.79
2826 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,449.49 rating
Confidence interval: 1,444.03 – 1,454.95
14308 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,398.49 rating
Confidence interval: 1,392.11 – 1,404.88
9737 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,408.48 rating
Confidence interval: 1,402.61 – 1,414.35
11732 votes
- Category
- instruction_following
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,374.85 rating
Confidence interval: 1,345.50 – 1,404.20
386 votes
- Category
- japanese
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,362.88 rating
Confidence interval: 1,340.13 – 1,385.63
702 votes
- Category
- korean
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,425.92 rating
Confidence interval: 1,419.98 – 1,431.87
11742 votes
- Category
- longer_query
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,422.35 rating
Confidence interval: 1,410.93 – 1,433.77
2633 votes
- Category
- math
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,423.86 rating
Confidence interval: 1,416.44 – 1,431.29
7002 votes
- Category
- multi_turn
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,398.95 rating
Confidence interval: 1,394.52 – 1,403.37
24894 votes
- Category
- non_english
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,419.90 rating
Confidence interval: 1,416.34 – 1,423.45
42071 votes
- Category
- overall
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,419.17 rating
Confidence interval: 1,402.05 – 1,436.30
1119 votes
- Category
- polish
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,407.11 rating
Confidence interval: 1,399.05 – 1,415.17
5423 votes
- Category
- russian
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
deepseek-v3.2-thinking
1,416.04 rating
Confidence interval: 1,399.86 – 1,432.22
1359 votes
- Category
- spanish
- Evaluated configuration
- deepseek-v3.2-thinking
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- MIT
0 selected Compare 0