deepseek-v3.2-exp-thinking
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsdeepseek-v3.2-exp-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-exp-thinking
1,459.77 rating
Confidence interval: 1,433.79 – 1,485.75
517 votes
- Category
- chinese
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,438.86 rating
Confidence interval: 1,425.59 – 1,452.12
1931 votes
- Category
- coding
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,388.26 rating
Confidence interval: 1,370.92 – 1,405.60
1192 votes
- Category
- creative_writing
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,441.40 rating
Confidence interval: 1,431.91 – 1,450.89
3891 votes
- Category
- english
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,414.49 rating
Confidence interval: 1,405.42 – 1,423.56
6410 votes
- Category
- exclude_ties
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,422.14 rating
Confidence interval: 1,394.12 – 1,450.16
426 votes
- Category
- expert
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,410.27 rating
Confidence interval: 1,364.02 – 1,456.52
147 votes
- Category
- french
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,436.98 rating
Confidence interval: 1,394.80 – 1,479.16
184 votes
- Category
- german
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,426.95 rating
Confidence interval: 1,418.38 – 1,435.52
4717 votes
- Category
- hard_prompts
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,443.66 rating
Confidence interval: 1,430.78 – 1,456.55
2062 votes
- Category
- hard_prompts_english
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,397.09 rating
Confidence interval: 1,383.37 – 1,410.82
1782 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,389.21 rating
Confidence interval: 1,374.84 – 1,403.57
1664 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,419.73 rating
Confidence interval: 1,394.72 – 1,444.75
501 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,443.51 rating
Confidence interval: 1,428.46 – 1,458.55
1421 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,433.34 rating
Confidence interval: 1,404.28 – 1,462.39
404 votes
- Category
- industry_mathematical
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,468.52 rating
Confidence interval: 1,441.08 – 1,495.95
443 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,438.26 rating
Confidence interval: 1,427.93 – 1,448.60
3203 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,396.31 rating
Confidence interval: 1,383.39 – 1,409.24
2095 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,400.51 rating
Confidence interval: 1,389.05 – 1,411.97
2559 votes
- Category
- instruction_following
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,348.97 rating
Confidence interval: 1,307.32 – 1,390.63
218 votes
- Category
- korean
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,411.07 rating
Confidence interval: 1,398.48 – 1,423.67
2107 votes
- Category
- longer_query
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,421.78 rating
Confidence interval: 1,395.24 – 1,448.31
477 votes
- Category
- math
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,412.66 rating
Confidence interval: 1,397.08 – 1,428.23
1401 votes
- Category
- multi_turn
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,404.54 rating
Confidence interval: 1,396.34 – 1,412.73
5107 votes
- Category
- non_english
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,424.95 rating
Confidence interval: 1,418.40 – 1,431.50
8998 votes
- Category
- overall
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,434.98 rating
Confidence interval: 1,406.04 – 1,463.93
397 votes
- Category
- polish
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,412.03 rating
Confidence interval: 1,390.47 – 1,433.59
657 votes
- Category
- russian
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
deepseek-v3.2-exp-thinking
1,408.58 rating
Confidence interval: 1,375.63 – 1,441.53
311 votes
- Category
- spanish
- Evaluated configuration
- deepseek-v3.2-exp-thinking
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- MIT
0 selected Compare 0