DeepSeek-Coder-V2
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsDeepSeek-Coder-V2
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-Coder-V2
1,200.79 rating
Confidence interval: 1,185.71 – 1,215.87
1712 votes
- Category
- chinese
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,250.69 rating
Confidence interval: 1,238.81 – 1,262.56
2671 votes
- Category
- coding
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,119.96 rating
Confidence interval: 1,106.62 – 1,133.29
2271 votes
- Category
- creative_writing
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,194.46 rating
Confidence interval: 1,186.42 – 1,202.49
8140 votes
- Category
- english
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,070.13 rating
Confidence interval: 1,060.69 – 1,079.56
9900 votes
- Category
- exclude_ties
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,181.15 rating
Confidence interval: 1,159.80 – 1,202.50
769 votes
- Category
- expert
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,185.09 rating
Confidence interval: 1,143.43 – 1,226.75
207 votes
- Category
- french
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,164.31 rating
Confidence interval: 1,137.96 – 1,190.66
516 votes
- Category
- german
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,206.67 rating
Confidence interval: 1,196.91 – 1,216.44
4439 votes
- Category
- hard_prompts
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,217.29 rating
Confidence interval: 1,205.39 – 1,229.18
2699 votes
- Category
- hard_prompts_english
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,155.10 rating
Confidence interval: 1,140.60 – 1,169.59
1796 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,122.10 rating
Confidence interval: 1,109.44 – 1,134.76
2513 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,163.14 rating
Confidence interval: 1,142.79 – 1,183.49
888 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,162.65 rating
Confidence interval: 1,149.78 – 1,175.52
2552 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,232.72 rating
Confidence interval: 1,218.65 – 1,246.79
1669 votes
- Category
- industry_mathematical
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,133.19 rating
Confidence interval: 1,112.36 – 1,154.01
847 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,238.68 rating
Confidence interval: 1,228.57 – 1,248.78
4344 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,170.22 rating
Confidence interval: 1,159.43 – 1,181.01
3882 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,180.17 rating
Confidence interval: 1,171.09 – 1,189.24
5614 votes
- Category
- instruction_following
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,126.45 rating
Confidence interval: 1,094.35 – 1,158.54
345 votes
- Category
- japanese
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,103.99 rating
Confidence interval: 1,072.08 – 1,135.91
399 votes
- Category
- korean
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,218.73 rating
Confidence interval: 1,204.84 – 1,232.61
1842 votes
- Category
- longer_query
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,241.28 rating
Confidence interval: 1,227.73 – 1,254.84
1858 votes
- Category
- math
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,176.52 rating
Confidence interval: 1,164.09 – 1,188.94
2683 votes
- Category
- multi_turn
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,181.94 rating
Confidence interval: 1,173.66 – 1,190.22
7007 votes
- Category
- non_english
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,191.17 rating
Confidence interval: 1,184.83 – 1,197.50
15147 votes
- Category
- overall
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,187.60 rating
Confidence interval: 1,173.50 – 1,201.69
1823 votes
- Category
- russian
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
DeepSeek-Coder-V2
1,153.18 rating
Confidence interval: 1,115.56 – 1,190.79
245 votes
- Category
- spanish
- Evaluated configuration
- DeepSeek-Coder-V2
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- DeepSeek License
0 selected Compare 0