DeepSeek-V3.1-Terminus (Thinking)
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsDeepSeek-V3.1-Terminus (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 / codinghuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,425.33 rating
Confidence interval: 1,402.04 – 1,448.62
633 votes
- Category
- coding
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,390.70 rating
Confidence interval: 1,363.00 – 1,418.41
435 votes
- Category
- creative_writing
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,428.50 rating
Confidence interval: 1,413.28 – 1,443.71
1467 votes
- Category
- english
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,405.93 rating
Confidence interval: 1,391.60 – 1,420.26
2430 votes
- Category
- exclude_ties
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,425.98 rating
Confidence interval: 1,411.63 – 1,440.34
1659 votes
- Category
- hard_prompts
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,431.90 rating
Confidence interval: 1,410.49 – 1,453.31
729 votes
- Category
- hard_prompts_english
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,414.89 rating
Confidence interval: 1,392.74 – 1,437.04
692 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,391.58 rating
Confidence interval: 1,368.08 – 1,415.08
609 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,457.54 rating
Confidence interval: 1,422.07 – 1,493.01
258 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,445.09 rating
Confidence interval: 1,419.98 – 1,470.20
530 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,468.25 rating
Confidence interval: 1,430.38 – 1,506.12
227 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,425.84 rating
Confidence interval: 1,408.34 – 1,443.33
1133 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,409.10 rating
Confidence interval: 1,387.99 – 1,430.22
761 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,404.74 rating
Confidence interval: 1,384.66 – 1,424.82
858 votes
- Category
- instruction_following
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,421.44 rating
Confidence interval: 1,399.21 – 1,443.67
680 votes
- Category
- longer_query
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,410.77 rating
Confidence interval: 1,386.37 – 1,435.17
571 votes
- Category
- multi_turn
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,405.23 rating
Confidence interval: 1,391.92 – 1,418.54
1912 votes
- Category
- non_english
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,419.14 rating
Confidence interval: 1,409.05 – 1,429.23
3379 votes
- Category
- overall
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,426.81 rating
Confidence interval: 1,387.96 – 1,465.65
205 votes
- Category
- polish
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
DeepSeek-V3.1-Terminus (Thinking)
1,436.01 rating
Confidence interval: 1,402.38 – 1,469.64
283 votes
- Category
- russian
- Evaluated configuration
- DeepSeek-V3.1-Terminus (Thinking)
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- MIT
0 selected Compare 0