LLM
DeepSeek-V3.1-Terminus
Update of DeepSeek-V3.1 with better language consistency and stronger code and search agents.
Levelmodel
ClassLLM
Parametersnot in the notes
Contextnot in the notes
Released22 Sep 2025
Opennessopen weights permissive
Runs onnot in the notes
Statusactive
Benchmark Results
vendor-reported
BrowseCompagents and tool use
Model card comparison table; mode not statedvendor-reported
38.5
050100
Score in %. Higher is better.
DeepSeek-V3.1-Terminus model card
GPQA Diamondknowledge and reasoning
Model card comparison table; mode not statedvendor-reported
80.7
050100
Score in %. Higher is better.
DeepSeek-V3.1-Terminus model card
LiveCodeBenchcoding
Model card comparison table; mode not statedvendor-reported
74.9
050100
Score in %. Higher is better.
DeepSeek-V3.1-Terminus model card
MMLU-Proknowledge and reasoning
Model card comparison table; mode not statedvendor-reported
85
050100
Score in %. Higher is better.
DeepSeek-V3.1-Terminus model card
SWE-bench Multilingualcoding
Model card comparison table; mode not statedvendor-reported
57.8
050100
Score in %. Higher is better.
DeepSeek-V3.1-Terminus model card
SWE-bench Verifiedcoding
Model card comparison table; mode not statedvendor-reported
68.4
050100
Score in %. Higher is better.
DeepSeek-V3.1-Terminus model card
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
successorcontinued pretrain
DeepSeek-V3.1 is the parent (successor)high confidencepress claimWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 3 models. Confidence and evidence are the notes' own.
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
- not in the notes
- 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
- API, consumer app, 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
- self_attn.o_proj parameters do not conform to the UE8M0 FP8 scale format in this checkpoint (known issue per model card)
- 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-V3.1-TerminusDeepSeek, LLM
DeepSeek-V3.1-TerminusDeepSeek, LLMUse CasesProcess Optimisation and Advanced Process ControlIndustrialClinical LLM (Open Weights)HealthcareTelecom 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.Organisations 1
Sources
- huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus
- api-docs.deepseek.com/news/news250922 https://api-docs.deepseek.com/news/news250922
- openrouter.ai/deepseek/deepseek-v3.1-terminus https://openrouter.ai/deepseek/deepseek-v3.1-terminus
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "DeepSeek-V3.1-Terminus", https://aurion.semai.id/models/deepseek-deepseek-v3-1-terminus/, records of October 2026.