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 · 2026-10-28 · rating
DeepSeek-V3.1
1,450.96 rating
Confidence interval: 1,435.07 – 1,466.84
1398 votes
- Category
- chinese
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,413.53 rating
Confidence interval: 1,402.00 – 1,425.05
2603 votes
- Category
- coding
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,387.64 rating
Confidence interval: 1,374.27 – 1,401.02
1977 votes
- Category
- creative_writing
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,429.79 rating
Confidence interval: 1,421.68 – 1,437.90
5998 votes
- Category
- english
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,405.38 rating
Confidence interval: 1,397.15 – 1,413.62
10422 votes
- Category
- exclude_ties
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,403.21 rating
Confidence interval: 1,381.73 – 1,424.70
734 votes
- Category
- expert
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,447.74 rating
Confidence interval: 1,413.42 – 1,482.05
288 votes
- Category
- french
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,410.80 rating
Confidence interval: 1,381.52 – 1,440.08
397 votes
- Category
- german
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,414.17 rating
Confidence interval: 1,406.41 – 1,421.94
6714 votes
- Category
- hard_prompts
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,419.63 rating
Confidence interval: 1,408.65 – 1,430.62
2872 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 · 2026-10-28 · rating
DeepSeek-V3.1
1,404.71 rating
Confidence interval: 1,392.83 – 1,416.59
2503 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 · 2026-10-28 · rating
DeepSeek-V3.1
1,378.08 rating
Confidence interval: 1,366.80 – 1,389.35
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 · 2026-10-28 · rating
DeepSeek-V3.1
1,416.54 rating
Confidence interval: 1,398.25 – 1,434.82
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 · 2026-10-28 · rating
DeepSeek-V3.1
1,433.32 rating
Confidence interval: 1,420.98 – 1,445.67
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 · 2026-10-28 · rating
DeepSeek-V3.1
1,413.28 rating
Confidence interval: 1,393.70 – 1,432.86
828 votes
- Category
- industry_mathematical
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,431.49 rating
Confidence interval: 1,412.43 – 1,450.54
939 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,426.54 rating
Confidence interval: 1,417.62 – 1,435.46
4632 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 · 2026-10-28 · rating
DeepSeek-V3.1
1,397.05 rating
Confidence interval: 1,386.85 – 1,407.26
3421 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,388.20 rating
Confidence interval: 1,378.39 – 1,398.01
3684 votes
- Category
- instruction_following
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,378.48 rating
Confidence interval: 1,347.41 – 1,409.55
334 votes
- Category
- japanese
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,337.01 rating
Confidence interval: 1,309.95 – 1,364.06
489 votes
- Category
- korean
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,399.30 rating
Confidence interval: 1,388.95 – 1,409.64
3242 votes
- Category
- longer_query
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,419.74 rating
Confidence interval: 1,401.42 – 1,438.06
979 votes
- Category
- math
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,399.93 rating
Confidence interval: 1,388.01 – 1,411.85
2398 votes
- Category
- multi_turn
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,399.53 rating
Confidence interval: 1,392.35 – 1,406.72
8608 votes
- Category
- non_english
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,419.51 rating
Confidence interval: 1,413.47 – 1,425.56
14606 votes
- Category
- overall
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,409.79 rating
Confidence interval: 1,390.75 – 1,428.83
1006 votes
- Category
- polish
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,404.67 rating
Confidence interval: 1,386.14 – 1,423.20
957 votes
- Category
- russian
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1
1,430.65 rating
Confidence interval: 1,400.78 – 1,460.52
411 votes
- Category
- spanish
- Evaluated configuration
- DeepSeek-V3.1
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- MIT
0 selected Compare 0