Levelmodel
ClassLLM
Parameters250B
Context1,000,000
Released22 Jul 2026
Opennessopen weights restricted
Runs onmulti-GPU node
Statusactive
Benchmark Results
vendor-reported
GPQA Diamondknowledge and reasoning
vendor-reported
86.3
050100
Score in %. Higher is better.
KMMLU-Proknowledge and reasoning
vendor-reported
78.4
050100
Score in %. Higher is better.
MMLU-Proknowledge and reasoning
vendor-reported
86.2
050100
Score in %. Higher is better.
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
successor
Where 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, 2 models. 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 Hybrid-attention MoE (softmax + linear attention, 320 routed + 1 shared experts), NoPE
- Total parameters
- 250B sources
- Active parameters
- 15B
- Checkpoint parameters
- –
- Context length
- 1,000,000 tokens
- 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 restricted
- Licence
- Upstage Solar License sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- multi-GPU node
- 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
- English, Korean, Japanese
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
Developer
Upstagestartup, South Korea
Model
Solar Open 2Upstage, LLM
R&D TopicsOpen-Weight Frontier Releases as Research SubstrateRegional or National Foundation Model Training (Continued Pretraining at 7B to 70B)
Use CasesIndonesian and Regional-Language LLMsPublic SectorBanking Customer Service AssistantsFinanceCitizen Service AssistantsPublic SectorClinical LLM (Open Weights)Healthcare+3 moreUse 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 2026
PT PegadaianIn production, 5 Jun 2026
Bank Central Asia (BCA)In production, 16 Mar 2026
Bank Central Asia (BCA)In production, 16 Mar 2026+14 moreDeployments of these use cases; none names this model.
PT Amman Mineral Nusa Tenggara (AMMAN)In production, 8 Jul 2026
PT PegadaianIn production, 5 Jun 2026
Bank Central Asia (BCA)In production, 16 Mar 2026
Bank Central Asia (BCA)In production, 16 Mar 2026+14 moreDeployments of these use cases; none names this model.Organisations 1
R&D topics 2
Open-Weight Frontier Releases as Research SubstrateUsing released weights as the base for downstream research.used byRegional or National Foundation Model Training (Continued Pretraining at 7B to 70B)Pretraining or continued pretraining a mid-size model to serve a national or regional lan…produced by
Sources
- The Upstage Blog | Upstage AI upstage.ai https://www.upstage.ai/blog
- huggingface.co/upstage/Solar-Open2-250B https://huggingface.co/upstage/Solar-Open2-250B
- huggingface.co/upstage https://huggingface.co/upstage
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Solar Open 2", https://aurion.semai.id/models/upstage-solar-open-2/, records of October 2026.