DeepSeek-V4.1-Flash-20260910 (Max)
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsDeepSeek-V4.1-Flash-20260910 (Max)
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 · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,503.59 rating
Confidence interval: 1,485.44 – 1,521.74
1053 votes
- Category
- chinese
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,502.97 rating
Confidence interval: 1,493.11 – 1,512.83
3855 votes
- Category
- coding
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,436.87 rating
Confidence interval: 1,425.06 – 1,448.68
2867 votes
- Category
- creative_writing
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,473.57 rating
Confidence interval: 1,464.93 – 1,482.21
5132 votes
- Category
- english
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,466.49 rating
Confidence interval: 1,458.60 – 1,474.39
10220 votes
- Category
- exclude_ties
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,501.32 rating
Confidence interval: 1,486.21 – 1,516.42
1518 votes
- Category
- expert
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,466.58 rating
Confidence interval: 1,440.26 – 1,492.91
546 votes
- Category
- french
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,464.76 rating
Confidence interval: 1,429.30 – 1,500.22
252 votes
- Category
- german
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,482.47 rating
Confidence interval: 1,475.42 – 1,489.52
8986 votes
- Category
- hard_prompts
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,487.81 rating
Confidence interval: 1,477.31 – 1,498.31
3381 votes
- Category
- hard_prompts_english
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,461.95 rating
Confidence interval: 1,449.75 – 1,474.14
2452 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,443.47 rating
Confidence interval: 1,432.64 – 1,454.29
3460 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,447.09 rating
Confidence interval: 1,429.52 – 1,464.65
1156 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,467.36 rating
Confidence interval: 1,454.72 – 1,480.01
2279 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,481.56 rating
Confidence interval: 1,462.19 – 1,500.93
879 votes
- Category
- industry_mathematical
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,489.58 rating
Confidence interval: 1,469.66 – 1,509.51
942 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,496.36 rating
Confidence interval: 1,487.93 – 1,504.78
5493 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,449.21 rating
Confidence interval: 1,438.81 – 1,459.61
3710 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,473.89 rating
Confidence interval: 1,464.90 – 1,482.87
4920 votes
- Category
- instruction_following
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,428.01 rating
Confidence interval: 1,392.37 – 1,463.64
302 votes
- Category
- japanese
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,429.61 rating
Confidence interval: 1,392.37 – 1,466.85
267 votes
- Category
- korean
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,474.24 rating
Confidence interval: 1,465.91 – 1,482.58
6108 votes
- Category
- longer_query
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,480.42 rating
Confidence interval: 1,459.09 – 1,501.76
730 votes
- Category
- math
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,461.50 rating
Confidence interval: 1,448.11 – 1,474.90
2040 votes
- Category
- multi_turn
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,449.71 rating
Confidence interval: 1,442.64 – 1,456.77
8840 votes
- Category
- non_english
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,463.48 rating
Confidence interval: 1,457.44 – 1,469.52
13976 votes
- Category
- overall
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,454.61 rating
Confidence interval: 1,419.59 – 1,489.62
250 votes
- Category
- polish
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,467.57 rating
Confidence interval: 1,453.96 – 1,481.17
1996 votes
- Category
- russian
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-11-06 · rating
DeepSeek-V4.1-Flash-20260910 (Max)
1,455.76 rating
Confidence interval: 1,429.58 – 1,481.94
489 votes
- Category
- spanish
- Evaluated configuration
- DeepSeek-V4.1-Flash-20260910 (Max)
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- MIT
0 selected Compare 0