Levelfamily
ClassLLM
Parametersnot in the notes
Contextnot in the notes
Released22 Apr 2026
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
From the model's own page; who made each picture and where it comes from are listed on the Image Credits page.
Benchmark Results
vendor-reportedindependent
Arena Text leaderboardhuman preference arena
1,465 ±7
1,2001,4001,600
Score in Elo; the axis starts at 1,200, as Elo has no zero. Higher is better.
Arena Text overall
Artificial Analysis Intelligence Index v4.3.2composite index
39
03060
Score in index. Higher is better.
AA leaderboard, 205 current models
Codeforces ratingcoding
DeepSWE v1.1coding
GPQA Diamondknowledge and reasoning
Humanity's Last Exam (HLE)knowledge and reasoning
LiveCodeBenchcoding
MMLU-Proknowledge and reasoning
SWE-bench Verifiedcoding
Terminal-Bench 2.1agents and tool use
Terminal-Bench 2.0agents and tool use
Terminal-Bench 4.0agents and tool use
Terminal-Bench 3.0agents and tool use
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Lineage
DeepSeek-V4.1-Flash belongs to this familymultimodal LLM10 Sep 2026552BDeepSeek-V4-Flash Vision-Exp belongs to this familymultimodal LLM1 Sep 2026DeepSeek-V4-Pro-0813 belongs to this familyLLM13 Aug 2026DeepSeek-V4-Flash belongs to this familyLLM24 Apr 2026284BDeepSeek-V4-Pro belongs to this familyLLM24 Apr 20261.6TDeepSeek-V4-Flash Base belongs to this familyLLM22 Apr 2026Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.
R&D Topics
Identity
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- MoE
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- text
- Output
- text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- open weights permissive
- Licence
- MIT License sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Industry Use Cases
No industry use case links this model.
Links
DeveloperDeepSeekstartup, China
DeepSeekstartup, ChinaModelDeepSeek V4DeepSeek, LLM
DeepSeek V4DeepSeek, LLMR&D TopicsEfficiency Architectures (MoE, Sparse Attention, Long Context)Open-Weight Frontier Releases as Research Substrate
Use CasesClinical LLM (Open Weights)HealthcareProcess Optimisation and Advanced Process ControlIndustrialTelecom Domain LLMs and BenchmarksTelecomUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
PT Amman Mineral Nusa Tenggara (AMMAN)In production, 8 Jul 2026MIND IDResearch, 14 Oct 2025
Conch CementIn production, 23 Jun 2025
PT Kalbe Morinaga IndonesiaIn production, Oct 2024+2 moreDeployments of these use cases; none names this model.
PT Amman Mineral Nusa Tenggara (AMMAN)In production, 8 Jul 2026MIND IDResearch, 14 Oct 2025Conch CementIn production, 23 Jun 2025PT Kalbe Morinaga IndonesiaIn production, Oct 2024+2 moreDeployments of these use cases; none names this model.Models 6
Organisations 1
Sources
- DeepSeek Releases V4: Open-Source 1.6T MoE with 1M Context rits.shanghai.nyu.edu https://rits.shanghai.nyu.edu/ai/deepseek-releases-v4-open-source-1-6t-moe-with-1m-context
- deepseek-ai/DeepSeek-V4-Pro , Hugging Face huggingface.co https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro
- deepseek-ai (DeepSeek) huggingface.co https://huggingface.co/deepseek-ai
- GitHub - NVIDIA/TensorRT-LLM: TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports github.com https://github.com/NVIDIA/TensorRT-LLM
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "DeepSeek V4", https://aurion.semai.id/models/deepseek-deepseek-v4/, records of October 2026.