GeekRadar / The comparison desk
COMPARE.
AI models
deepseek

deepseek-v4-pro-high-20260813

Model evaluation

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

deepseek-v4-pro-high-20260813 1445.6 deepseek-v4-pro-high-20260813 · 95% interval 1439.0–1452.1 · 9,800 votes · 2026-10-15

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-v4-pro-high-20260813

1,480.01 rating

Confidence interval: 1,457.59 – 1,502.43

705 votes

Category
chinese
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,468.63 rating

Confidence interval: 1,457.31 – 1,479.95

2807 votes

Category
coding
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,439.02 rating

Confidence interval: 1,425.15 – 1,452.88

1985 votes

Category
creative_writing
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,457.98 rating

Confidence interval: 1,448.24 – 1,467.71

3765 votes

Category
english
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,442.04 rating

Confidence interval: 1,433.36 – 1,450.71

7168 votes

Category
exclude_ties
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,458.96 rating

Confidence interval: 1,440.57 – 1,477.35

1029 votes

Category
expert
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,444.70 rating

Confidence interval: 1,411.55 – 1,477.85

314 votes

Category
french
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,457.55 rating

Confidence interval: 1,449.85 – 1,465.26

6532 votes

Category
hard_prompts
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,463.02 rating

Confidence interval: 1,451.02 – 1,475.03

2498 votes

Category
hard_prompts_english
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,441.84 rating

Confidence interval: 1,427.90 – 1,455.79

1802 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,423.68 rating

Confidence interval: 1,411.23 – 1,436.12

2452 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,457.62 rating

Confidence interval: 1,437.37 – 1,477.88

825 votes

Category
industry_legal_and_government
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,457.46 rating

Confidence interval: 1,442.38 – 1,472.54

1528 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,442.95 rating

Confidence interval: 1,416.96 – 1,468.95

516 votes

Category
industry_mathematical
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,448.29 rating

Confidence interval: 1,425.17 – 1,471.40

624 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,461.97 rating

Confidence interval: 1,452.55 – 1,471.39

4091 votes

Category
industry_software_and_it_services
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,442.91 rating

Confidence interval: 1,430.97 – 1,454.85

2627 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,447.93 rating

Confidence interval: 1,437.67 – 1,458.19

3481 votes

Category
instruction_following
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,447.77 rating

Confidence interval: 1,407.10 – 1,488.44

198 votes

Category
korean
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,457.97 rating

Confidence interval: 1,448.74 – 1,467.19

4561 votes

Category
longer_query
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,440.47 rating

Confidence interval: 1,412.71 – 1,468.23

408 votes

Category
math
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,453.75 rating

Confidence interval: 1,438.39 – 1,469.12

1564 votes

Category
multi_turn
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,430.33 rating

Confidence interval: 1,422.42 – 1,438.23

6035 votes

Category
non_english
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,445.55 rating

Confidence interval: 1,438.98 – 1,452.12

9800 votes

Category
overall
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,446.60 rating

Confidence interval: 1,429.98 – 1,463.21

1236 votes

Category
russian
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

deepseek-v4-pro-high-20260813

1,433.74 rating

Confidence interval: 1,401.43 – 1,466.05

298 votes

Category
spanish
Evaluated configuration
deepseek-v4-pro-high-20260813
Evaluation type
human preference

Run it locally

Inference · memory estimate

deepseek-v4-pro-high-20260813

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
MIT