DeepSeek V3 0324
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsDeepSeek V3 0324
AI model Released
- Context window
- 163,840 tokens
- Maximum output
- 147,456 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 / chinesehuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,390.31 rating
Confidence interval: 1,379.44 – 1,401.17
3034 votes
- Category
- chinese
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,367.75 rating
Confidence interval: 1,360.98 – 1,374.51
8334 votes
- Category
- coding
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,364.02 rating
Confidence interval: 1,356.05 – 1,371.99
5990 votes
- Category
- creative_writing
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,388.92 rating
Confidence interval: 1,383.96 – 1,393.87
21422 votes
- Category
- english
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,345.27 rating
Confidence interval: 1,339.93 – 1,350.61
31458 votes
- Category
- exclude_ties
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,350.46 rating
Confidence interval: 1,338.17 – 1,362.75
2351 votes
- Category
- expert
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,385.04 rating
Confidence interval: 1,360.53 – 1,409.56
594 votes
- Category
- french
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,373.75 rating
Confidence interval: 1,356.31 – 1,391.19
1223 votes
- Category
- german
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,364.77 rating
Confidence interval: 1,359.59 – 1,369.95
18588 votes
- Category
- hard_prompts
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,378.84 rating
Confidence interval: 1,372.19 – 1,385.50
9015 votes
- Category
- hard_prompts_english
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,349.18 rating
Confidence interval: 1,341.67 – 1,356.68
6855 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,356.86 rating
Confidence interval: 1,349.94 – 1,363.77
8019 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,378.90 rating
Confidence interval: 1,367.75 – 1,390.04
2905 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,381.66 rating
Confidence interval: 1,374.52 – 1,388.80
7628 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,364.14 rating
Confidence interval: 1,353.46 – 1,374.82
2947 votes
- Category
- industry_mathematical
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,383.14 rating
Confidence interval: 1,371.51 – 1,394.78
2656 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,377.88 rating
Confidence interval: 1,372.24 – 1,383.52
14363 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,364.74 rating
Confidence interval: 1,358.37 – 1,371.11
10285 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,344.46 rating
Confidence interval: 1,338.61 – 1,350.31
12410 votes
- Category
- instruction_following
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,332.93 rating
Confidence interval: 1,314.04 – 1,351.81
1056 votes
- Category
- japanese
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,318.88 rating
Confidence interval: 1,299.36 – 1,338.41
969 votes
- Category
- korean
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,352.03 rating
Confidence interval: 1,345.33 – 1,358.73
8531 votes
- Category
- longer_query
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,372.55 rating
Confidence interval: 1,362.26 – 1,382.84
3166 votes
- Category
- math
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,388.53 rating
Confidence interval: 1,381.33 – 1,395.72
7685 votes
- Category
- multi_turn
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,357.86 rating
Confidence interval: 1,353.07 – 1,362.64
23546 votes
- Category
- non_english
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,374.59 rating
Confidence interval: 1,370.74 – 1,378.44
44973 votes
- Category
- overall
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,368.45 rating
Confidence interval: 1,356.47 – 1,380.42
2736 votes
- Category
- polish
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,373.19 rating
Confidence interval: 1,363.66 – 1,382.72
3573 votes
- Category
- russian
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
DeepSeek V3 0324
1,357.92 rating
Confidence interval: 1,338.62 – 1,377.22
987 votes
- Category
- spanish
- Evaluated configuration
- deepseek-v3-0324
- Evaluation type
- human preference
Run it locally
API cost
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.
DeepSeek V3 0324
Capabilities
- Context window
- 163,840 tokens
- Maximum output
- 147,456 tokens
- Reasoning
- No
- Tool calling
- Yes
- Open weights
- Yes
- Knowledge cutoff
- 2024-07-31
- Model license
- MIT
Input modalities
- text
Output modalities
- text
Processing & platform
- Architecture
- deepseek_v3
0 selected Compare 0