DeepSeek-V3.1 (Thinking)
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsDeepSeek-V3.1 (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 · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,468.40 rating
Confidence interval: 1,450.27 – 1,486.53
1142 votes
- Category
- chinese
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,416.85 rating
Confidence interval: 1,403.38 – 1,430.31
1874 votes
- Category
- coding
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,400.83 rating
Confidence interval: 1,386.09 – 1,415.56
1618 votes
- Category
- creative_writing
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,432.07 rating
Confidence interval: 1,423.10 – 1,441.04
4661 votes
- Category
- english
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,403.09 rating
Confidence interval: 1,394.12 – 1,412.06
8140 votes
- Category
- exclude_ties
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,404.83 rating
Confidence interval: 1,380.22 – 1,429.45
538 votes
- Category
- expert
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,401.91 rating
Confidence interval: 1,357.94 – 1,445.89
183 votes
- Category
- french
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,408.28 rating
Confidence interval: 1,376.17 – 1,440.38
323 votes
- Category
- german
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,416.81 rating
Confidence interval: 1,408.19 – 1,425.43
5084 votes
- Category
- hard_prompts
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,427.37 rating
Confidence interval: 1,414.69 – 1,440.05
2129 votes
- Category
- hard_prompts_english
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,408.93 rating
Confidence interval: 1,395.54 – 1,422.32
1936 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,393.43 rating
Confidence interval: 1,380.95 – 1,405.92
2204 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,417.19 rating
Confidence interval: 1,396.58 – 1,437.80
770 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,427.75 rating
Confidence interval: 1,414.11 – 1,441.39
1831 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,437.39 rating
Confidence interval: 1,413.56 – 1,461.22
561 votes
- Category
- industry_mathematical
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,443.69 rating
Confidence interval: 1,421.16 – 1,466.21
688 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,426.99 rating
Confidence interval: 1,416.88 – 1,437.10
3464 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,404.38 rating
Confidence interval: 1,392.95 – 1,415.82
2723 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,400.35 rating
Confidence interval: 1,389.25 – 1,411.45
2832 votes
- Category
- instruction_following
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,359.46 rating
Confidence interval: 1,322.92 – 1,396.01
258 votes
- Category
- japanese
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,336.87 rating
Confidence interval: 1,305.34 – 1,368.40
374 votes
- Category
- korean
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,421.59 rating
Confidence interval: 1,409.64 – 1,433.55
2375 votes
- Category
- longer_query
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,414.81 rating
Confidence interval: 1,392.82 – 1,436.80
658 votes
- Category
- math
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,407.58 rating
Confidence interval: 1,393.69 – 1,421.46
1816 votes
- Category
- multi_turn
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,399.91 rating
Confidence interval: 1,392.08 – 1,407.74
6797 votes
- Category
- non_english
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,416.60 rating
Confidence interval: 1,409.97 – 1,423.22
11458 votes
- Category
- overall
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,404.84 rating
Confidence interval: 1,384.32 – 1,425.37
787 votes
- Category
- polish
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,399.24 rating
Confidence interval: 1,379.05 – 1,419.43
727 votes
- Category
- russian
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1 (Thinking)
1,411.63 rating
Confidence interval: 1,381.67 – 1,441.58
388 votes
- Category
- spanish
- Evaluated configuration
- DeepSeek-V3.1 (Thinking)
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- MIT
0 selected Compare 0