DeepSeek-V3.1-Terminus
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsDeepSeek-V3.1-Terminus
AI model
- Context window
- 163,840 tokens
- Open weights
- Yes
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 / codinghuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,406.69 rating
Confidence interval: 1,386.17 – 1,427.21
771 votes
- Category
- coding
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,403.32 rating
Confidence interval: 1,375.92 – 1,430.72
446 votes
- Category
- creative_writing
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,418.74 rating
Confidence interval: 1,404.20 – 1,433.29
1583 votes
- Category
- english
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,401.88 rating
Confidence interval: 1,388.04 – 1,415.72
2583 votes
- Category
- exclude_ties
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,406.10 rating
Confidence interval: 1,392.90 – 1,419.30
1901 votes
- Category
- hard_prompts
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,406.78 rating
Confidence interval: 1,387.08 – 1,426.48
850 votes
- Category
- hard_prompts_english
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,387.37 rating
Confidence interval: 1,365.57 – 1,409.17
718 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,382.40 rating
Confidence interval: 1,359.16 – 1,405.64
626 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,407.49 rating
Confidence interval: 1,371.90 – 1,443.09
263 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,451.35 rating
Confidence interval: 1,427.15 – 1,475.55
571 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,451.01 rating
Confidence interval: 1,413.91 – 1,488.11
259 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,409.46 rating
Confidence interval: 1,393.34 – 1,425.58
1279 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,407.73 rating
Confidence interval: 1,387.03 – 1,428.44
791 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,380.70 rating
Confidence interval: 1,362.85 – 1,398.55
1018 votes
- Category
- instruction_following
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,395.87 rating
Confidence interval: 1,376.20 – 1,415.54
841 votes
- Category
- longer_query
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,401.74 rating
Confidence interval: 1,363.20 – 1,440.27
216 votes
- Category
- math
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,387.89 rating
Confidence interval: 1,365.29 – 1,410.49
658 votes
- Category
- multi_turn
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,407.50 rating
Confidence interval: 1,394.61 – 1,420.38
2026 votes
- Category
- non_english
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,417.10 rating
Confidence interval: 1,407.38 – 1,426.82
3609 votes
- Category
- overall
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,405.00 rating
Confidence interval: 1,366.92 – 1,443.08
229 votes
- Category
- polish
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus
1,423.53 rating
Confidence interval: 1,392.74 – 1,454.32
304 votes
- Category
- russian
- Evaluated configuration
- DeepSeek-V3.1-Terminus
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,406.80 rating
Confidence interval: 1,386.27 – 1,427.32
771 votes
- Category
- coding
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,402.66 rating
Confidence interval: 1,375.29 – 1,430.02
447 votes
- Category
- creative_writing
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,418.95 rating
Confidence interval: 1,404.39 – 1,433.52
1580 votes
- Category
- english
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,401.93 rating
Confidence interval: 1,388.09 – 1,415.77
2583 votes
- Category
- exclude_ties
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,405.93 rating
Confidence interval: 1,392.73 – 1,419.13
1902 votes
- Category
- hard_prompts
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,406.70 rating
Confidence interval: 1,386.99 – 1,426.40
850 votes
- Category
- hard_prompts_english
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,387.44 rating
Confidence interval: 1,365.64 – 1,409.25
718 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,382.53 rating
Confidence interval: 1,359.32 – 1,405.74
627 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,407.28 rating
Confidence interval: 1,371.67 – 1,442.88
263 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,451.45 rating
Confidence interval: 1,427.20 – 1,475.69
570 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,451.12 rating
Confidence interval: 1,414.01 – 1,488.23
259 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,409.55 rating
Confidence interval: 1,393.42 – 1,425.67
1279 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,407.85 rating
Confidence interval: 1,387.14 – 1,428.55
791 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,380.36 rating
Confidence interval: 1,362.52 – 1,398.20
1019 votes
- Category
- instruction_following
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,395.57 rating
Confidence interval: 1,375.91 – 1,415.23
842 votes
- Category
- longer_query
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,401.81 rating
Confidence interval: 1,363.25 – 1,440.36
216 votes
- Category
- math
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,387.92 rating
Confidence interval: 1,365.32 – 1,410.52
658 votes
- Category
- multi_turn
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,407.42 rating
Confidence interval: 1,394.55 – 1,420.30
2028 votes
- Category
- non_english
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,417.10 rating
Confidence interval: 1,407.38 – 1,426.83
3608 votes
- Category
- overall
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,405.03 rating
Confidence interval: 1,366.95 – 1,443.12
229 votes
- Category
- polish
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
DeepSeek-V3.1-Terminus
1,422.36 rating
Confidence interval: 1,391.60 – 1,453.12
305 votes
- Category
- russian
- Evaluated configuration
- deepseek-v3.1-terminus
- Evaluation type
- human preference
Run it locally
Capabilities
- Context window
- 163,840 tokens
- Open weights
- Yes
- Model license
- mit
Input modalities
- text
Output modalities
- text
Processing & platform
- Architecture
- deepseek_v3
0 selected Compare 0