DeepSeek-V3.1
DeepSeek- Arena score
- 1420
- Among open models
- #34of 148
- Among all on Arena
- #118
- Votes
- 14,583
Measured on DeepSeek-V3.1, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Chinese1468#25#931.1K
- French1448#24#92287
- Medicine & health1444#29#92684
- Applied math1438#30#97560
- Science1434#34#1202.3K
- English1432#33#1174.7K
- Spanish1431#29#102411
- Software & IT1427#46#1464.6K
- Hard prompts, English1427#44#1372.1K
- Long prompts1421#29#1102.4K
- Math1420#39#126977
- Coding1417#50#1571.9K
- Hard prompts1417#42#1415.1K
- Legal & government1417#40#1401K
- German1412#31#115396
- Polish1410#30#1131K
- Business & finance1409#41#1301.9K
- Multi-turn1407#43#1461.8K
- Excluding ties1406#36#12410.4K
- Expert1405#49#153731
- Writing & literature1404#27#1112.7K
- Russian1404#34#129956
- Creative writing1401#23#1011.6K
- Instructions1400#38#1332.8K
- Non-English1400#39#1348.6K
- Media & sports1394#29#1132.2K
- Japanese1379#27#102334
- Korean1338#41#150490
About as strong, smaller
Compare
gemma-4-26B-A4B-itGoogle143425.8B

Qwen3.8-27BQwen143727.8B

Qwen3.5-27BQwen140927.8B

gemma-4-31B-itGoogle144331.3B
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM Studiobartowski/deepseek-ai_DeepSeek-V3.1-GGUF9 builds
- MLX · Apple silicon: mlx-lm, LM Studiomlx-community/DeepSeek-V3.1-4bit3 builds
- AWQ · vLLM, SGLangQuantTrio/DeepSeek-V3.1-AWQ3 builds
Most downloaded
- deepseek-ai_DeepSeek-V3.1-GGUFbartowski · Quantization18.5K downloads
- DeepSeek-V3.1-GGUFunsloth · Quantization9.2K downloads
- DeepSeek-V3.1-NVFP4nvidia · Fine-tune2.4K downloads
- deepseek-ai.DeepSeek-V3.1-GGUFDevQuasar · Quantization1.6K downloads
- DeepSeek-V3.1-4bitmlx-community · Quantization1.1K downloads
BenchClub runs
Not runnable yet
Runs open once a DeepSeek-V3.1 build is registered.
More from DeepSeek
See more
DeepSeek-V3.29.6M685B

DeepSeek-V4-Flash-07312M304B

DeepSeek-V4.1-Flash1.6M763B

DeepSeek-V4-Flash1.2M291B
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