deepseek-v3.1
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsdeepseek-v3.1
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-v3.1
1,451.12 rating
Confidence interval: 1,435.23 – 1,467.00
1398 votes
- Category
- chinese
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
deepseek-v3.1
1,413.75 rating
Confidence interval: 1,402.23 – 1,425.28
2604 votes
- Category
- coding
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
deepseek-v3.1
1,387.97 rating
Confidence interval: 1,374.59 – 1,401.34
1978 votes
- Category
- creative_writing
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
deepseek-v3.1
1,429.76 rating
Confidence interval: 1,421.65 – 1,437.87
5997 votes
- Category
- english
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
deepseek-v3.1
1,405.55 rating
Confidence interval: 1,397.31 – 1,413.78
10425 votes
- Category
- exclude_ties
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
deepseek-v3.1
1,403.28 rating
Confidence interval: 1,381.80 – 1,424.77
734 votes
- Category
- expert
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
deepseek-v3.1
1,447.27 rating
Confidence interval: 1,412.95 – 1,481.59
288 votes
- Category
- french
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
deepseek-v3.1
1,411.54 rating
Confidence interval: 1,382.28 – 1,440.80
398 votes
- Category
- german
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
deepseek-v3.1
1,414.28 rating
Confidence interval: 1,406.52 – 1,422.05
6717 votes
- Category
- hard_prompts
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
deepseek-v3.1
1,419.67 rating
Confidence interval: 1,408.69 – 1,430.66
2873 votes
- Category
- hard_prompts_english
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
deepseek-v3.1
1,404.77 rating
Confidence interval: 1,392.90 – 1,416.65
2504 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
deepseek-v3.1
1,378.11 rating
Confidence interval: 1,366.83 – 1,389.38
2743 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
deepseek-v3.1
1,416.29 rating
Confidence interval: 1,398.00 – 1,434.58
1001 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
deepseek-v3.1
1,433.42 rating
Confidence interval: 1,421.08 – 1,445.77
2290 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
deepseek-v3.1
1,413.71 rating
Confidence interval: 1,394.14 – 1,433.29
829 votes
- Category
- industry_mathematical
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
deepseek-v3.1
1,431.32 rating
Confidence interval: 1,412.26 – 1,450.38
938 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
deepseek-v3.1
1,426.72 rating
Confidence interval: 1,417.80 – 1,435.64
4634 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
deepseek-v3.1
1,397.16 rating
Confidence interval: 1,386.95 – 1,407.37
3421 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
deepseek-v3.1
1,388.24 rating
Confidence interval: 1,378.43 – 1,398.05
3685 votes
- Category
- instruction_following
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
deepseek-v3.1
1,378.31 rating
Confidence interval: 1,347.25 – 1,409.37
334 votes
- Category
- japanese
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
deepseek-v3.1
1,337.83 rating
Confidence interval: 1,310.83 – 1,364.83
491 votes
- Category
- korean
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
deepseek-v3.1
1,399.52 rating
Confidence interval: 1,389.18 – 1,409.87
3243 votes
- Category
- longer_query
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
deepseek-v3.1
1,420.08 rating
Confidence interval: 1,401.76 – 1,438.39
980 votes
- Category
- math
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
deepseek-v3.1
1,400.01 rating
Confidence interval: 1,388.09 – 1,411.92
2399 votes
- Category
- multi_turn
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
deepseek-v3.1
1,399.76 rating
Confidence interval: 1,392.58 – 1,406.94
8613 votes
- Category
- non_english
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
deepseek-v3.1
1,419.61 rating
Confidence interval: 1,413.57 – 1,425.65
14610 votes
- Category
- overall
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
deepseek-v3.1
1,409.83 rating
Confidence interval: 1,390.79 – 1,428.87
1006 votes
- Category
- polish
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
deepseek-v3.1
1,404.74 rating
Confidence interval: 1,386.23 – 1,423.24
958 votes
- Category
- russian
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
deepseek-v3.1
1,430.55 rating
Confidence interval: 1,400.68 – 1,460.43
411 votes
- Category
- spanish
- Evaluated configuration
- deepseek-v3.1
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- MIT
0 selected Compare 0