DeepSeek-V3-0324
DeepSeek- Arena score
- 1375
- Among open models
- #57of 148
- Among all on Arena
- #184
- Votes
- 44,915
Measured on DeepSeek-V3 (0324), the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- Chinese1390#61#1893K
- English1389#57#18021.4K
- Multi-turn1389#53#1717.7K
- French1385#50#167593
- Medicine & health1383#57#1812.7K
- Science1382#60#1897.6K
- Legal & government1379#56#1812.9K
- Hard prompts, English1379#62#1929K
- Software & IT1378#65#20214.3K
- German1374#45#1551.2K
- Russian1373#51#1743.6K
- Math1372#60#1953.2K
- Polish1369#44#1602.7K
- Coding1368#71#2128.3K
- Hard prompts1365#61#19718.6K
- Writing & literature1365#49#17210.3K
- Creative writing1364#40#1536K
- Applied math1364#66#2052.9K
- Non-English1358#56#18823.5K
- Spanish1358#58#186983
- Media & sports1357#47#1648K
- Long prompts1352#63#2038.5K
- Expert1350#69#2042.3K
- Business & finance1349#63#1976.9K
- Excluding ties1345#57#18431.4K
- Instructions1345#61#19712.4K
- Japanese1333#36#1441.1K
- Korean1320#45#161964
| Model | Params | Score |
|---|---|---|
| 684B | 1333 | |
| 685B | 1375 |
About as strong, smaller
Compare
gemma-4-26B-A4B-itGoogle143425.8B

Qwen3.8-27BQwen143727.8B

Qwen3.5-27BQwen140927.8B
granite-4.2-30bIBM Granite136229.3B
Discussion
1 post this week
Built on it
Ways to run it
- GGUF · llama.cpp, Ollama, LM StudioMaziyarPanahi/DeepSeek-V3-0324-GGUF19 builds
- MLX · Apple silicon: mlx-lm, LM Studiomlx-community/DeepSeek-V3-0324-5bit1 build
- AWQ · vLLM, SGLangQuixiAI/DeepSeek-V3-0324-AWQ2 builds
Most downloaded
- DeepSeek-V3-0324-GGUFMaziyarPanahi · Quantization36.5K downloads
- DeepSeek-V3-0324-NVFP4nvidia · Fine-tune10.1K downloads
- DeepSeek-V3-0324-GGUFunsloth · Quantization3.9K downloads
- DeepSeek-V3-0324-GGUF-UDunsloth · Quantization2.3K downloads
- deepseek-ai_DeepSeek-V3-0324-GGUFbartowski · Quantization1.5K downloads
BenchClub runs
Not runnable yet
Runs open once a DeepSeek-V3-0324 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