DeepSeek-V4.1-Flash
DeepSeek- Arena score
- 1464
- Among open models
- #6of 148
- Among all on Arena
- #40
- Votes
- 13,547
Measured on DeepSeek-V4.1-Flash-20260910 (Max), the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
Top 10 among open models in#1Medicine & health#3Coding#3Software & IT#3Russian
CategoryScoreOpen rankArena rankVotes
- Chinese1505#10#531K
- Coding1504#3#203.7K
- Expert1503#4#281.4K
- Software & IT1496#3#245.3K
- Medicine & health1490#1#20906
- Hard prompts, English1488#5#273.3K
- Hard prompts1483#5#368.7K
- Applied math1479#8#43815
- Math1479#7#34691
- Long prompts1474#6#425.8K
- English1474#7#365K
- Instructions1473#5#304.7K
- French1470#9#51527
- Russian1469#3#361.9K
- Science1468#9#482.2K
- Excluding ties1467#5#399.9K
- Business & finance1463#4#322.4K
- Multi-turn1462#8#472K
- German1460#6#44245
- Spanish1456#10#49474
- Polish1453#6#49243
- Non-English1450#6#428.6K
- Writing & literature1449#8#453.6K
- Legal & government1447#16#761.1K
- Media & sports1444#5#373.3K
- Creative writing1438#8#512.8K
- Japanese1430#10#47289
- Korean1423#7#44244
About as strong, smaller
Compare
GLM-5.3-FlashZ.ai1472321B
Discussion
- What It Actually Costs to Run DeepSeek V4.1 Flash Locally?Kai · Sep 13, 20266.6K likes
- DeepSeek v4.1 FlashLiwink · Sep 10, 20261K points
- DeepSeek-V4.1 Flash: The Most Insane Optimization So Farbycloud · Oct 10, 20264.4K likes
- DeepSeek-v4.1-Flash-1017theykk · Oct 17, 2026959 points
- The New DeepSeek V4.1 Flash Is INSANE – The BEST Open Model Yet?Bijan Bowen · Oct 18, 20262.3K likes
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studioantirez/deepseek-v4.1-flash-gguf24 builds
- MLX · Apple silicon: mlx-lm, LM StudioTensorFold/DeepSeek-V4.1-Flash-MLX-2bit-MTP14 builds
- GPTQ · vLLM, SGLangINCModel3/DeepSeek-V4.1-Flash-W4A16-Engram-AutoRound2 builds
Most downloaded
- deepseek-v4.1-flash-ggufantirez · Quantization812.8K downloads
- deepseek-v4.1-flash-ggufkyuz0 · Quantization71.9K downloads
- DeepSeek-V4.1-Flash-NVFP4nvidia · Quantization36.6K downloads
- DeepSeek-V4.1-Flash-UNCENSORED-FP8dealignai · Quantization17.5K downloads
- DeepSeek-V4.1-Flash-MXFP4-Mixed-CT-AutoRoundintel-ai · Quantization12.2K downloads
BenchClub runs
Not runnable yet
Runs open once a DeepSeek-V4.1-Flash build is registered.
More from DeepSeek
See more
DeepSeek-V3.29.6M685B

DeepSeek-V4-Flash-07312M304B

DeepSeek-V4-Flash1.2M291B

DeepSeek-V4-Pro309.2K1.6T
Other >300B models
See more
GLM-5.3-FlashZ.ai6.4M321B
InklingThinking Machines1.5M952B
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16NVIDIA1M561B

Kimi-K3Moonshot AI768.9K2.8T