multimodal LLM
GPT-6 Astra
Flagship of the GPT-6 family for complex reasoning and coding; text and image in, text out, with function calling, web search, file search and computer use. Available via OpenAI API, ChatGPT, GitHub Copilot.
Levelmodel
Classmultimodal LLM
Parametersnot in the notes
Context1,050,000
Released3 Sep 2026
Opennessproprietary
Runs onnot in the notes
Statusactive
Benchmark Results
vendor-reportedmaintainer-runindependent
ARC-AGI-2knowledge and reasoning
$1.12/taskvendor-reported
95
050100
Score in %. Higher is better.
ARC-AGI-3knowledge and reasoning
with OpenAI adapter harness (apiyi citing Latent Space)vendor-reported
99.9
050100
Score in %. Higher is better.
Conflicting figures across sourcesvendor-reported
98.6
050100
Score in %. Higher is better.
direct, about 63 to 66% (apiyi citing Latent Space)vendor-reported
no score in the notes
Arena Text leaderboardhuman preference arena
maxindependent
1,475 ±7
1,2001,4001,600
Score in Elo; the axis starts at 1,200, as Elo has no zero. Higher is better.
rank 35, Arena Text overall
Arena Vision leaderboardhuman preference arena
maxindependent
1,286 ±11
1,2701,2901,310
Score in Elo; the axis starts at 1,270, as Elo has no zero. Higher is better.
rank 19 of 165, Arena Vision overall, style control default, 165 models
Artificial Analysis Intelligence Index v4.3.2composite index
max; 52.67 per secondaryindependent
53
090180
Score in index. Higher is better.
rank 7 of 205, AA leaderboard, 205 current models
benchlm.ai frontier compositecomposite index
vendor-reported
85
090180
Score in index. Higher is better.
benchlm.ai frontier top 6
DeepSWE v1.1coding
vendor-reported
74.1
050100
Score in %. Higher is better.
Epoch Capabilities Index (ECI)composite index
Epoch data file of 15 Oct 2026: 0.41 behind Claude Opus 5.5, within each other's confidence intervalsmaintainer-run
166.41 CI 163.35 to 171.23
090180
Score in index. Higher is better.
rank 2, Epoch AI Benchmarking Hub
vendor-reported
97.6
050100
Score in %. Higher is better.
Solved 2 of 68 problemsmaintainer-run
3
050100
Score in %. Higher is better.
Epoch AI Benchmarking Hub
GPQA Diamondknowledge and reasoning
vendor-reported
96
050100
Score in %. Higher is better.
vendor-reported
96
050100
Score in %. Higher is better.
rank 1, BenchLM aggregator, top score
OpenAI MRCR v2long context
512K to 1Mvendor-reported
96.3
050100
Score in %. Higher is better.
OSWorld 2.0agents and tool use
vendor-reported
72.6
050100
Score in %. Higher is better.
Terminal-Bench 4.0agents and tool use
57.9% to 58.2% across sourcesvendor-reported
57.9
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
GPT-5.6 Sol is the parent (successor)medium confidencenotesGPT-6 Luna is a child (successor)medium confidencenotesGPT-6 Sol is a child (successor)medium confidencenotesWhere 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, 6 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
- not in the notes Not disclosed; pre-trained on more than 100,000 GPUs at Stargate Texas (secondary, citing Axios)
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- 1,050,000 tokens
- Input
- text, image
- 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
- proprietary
- Licence
- Proprietary sources
- Access routes
- API, consumer app, cloud marketplace
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- Vendor cloud/API only (T1). Max output 128K. Staged rollout from 3 Sep 2026; second OpenAI post 9 Sep 2026.
- 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
DeveloperOpenAIfrontier lab, USA
OpenAIfrontier lab, USAModelGPT-6 AstraOpenAI, multimodal LLM
GPT-6 AstraOpenAI, multimodal LLMR&D TopicsFrontier Pretraining Scaling
Use CasesIndustrial Copilots and Maintenance AssistantsIndustrialClinical LLM (Frontier Proprietary)HealthcarePharma Documents, Regulatory and Life-Science R&DHealthcareAmbient Clinical ScribingHealthcare+2 moreUse cases of models in the same R&D topic; none is recorded for this model itself.
Who Runs It
PT Pertamina Geothermal EnergyIn production, 14 Jul 2026
Banner HealthIn production, 11 Jan 2026CommureIn production, 11 Jan 2026FlatironIn production, 11 Jan 2026+39 moreDeployments of these use cases; none names this model.
PT Pertamina Geothermal EnergyIn production, 14 Jul 2026Banner HealthIn production, 11 Jan 2026CommureIn production, 11 Jan 2026FlatironIn production, 11 Jan 2026+39 moreDeployments of these use cases; none names this model.Models 4
Organisations 1
Sources
- Models | OpenAI API developers.openai.com https://developers.openai.com/api/docs/models
- openai.com/index/gpt-6-astra https://openai.com/index/gpt-6-astra/
- openai.com/news/rss.xml https://openai.com/news/rss.xml
- OpenAI Launches GPT-6 Astra, Pricing, Benchmarks and Who Gets It First pasqualepillitteri.it https://pasqualepillitteri.it/en/news/14246/openai-launches-gpt-6-astra-pricing-benchmarks
- GPT-6 Astra Is Live: OpenAI's New Flagship Open for Calls - API易文档中心 docs.apiyi.com https://docs.apiyi.com/en/news/gpt-6-astra-launch
- OpenAI Releases GPT-6 Astra for Coding and Computer Use infoq.com https://infoq.com/news/2026/09/openai-gpt6-astra
- Supported AI models in GitHub Copilot - GitHub Docs docs.github.com https://docs.github.com/en/copilot/reference/ai-models/supported-models
- GPQA Leaderboard (October 2026): GPT-6 Astra Leads at 96% benchlm.ai https://www.benchlm.ai/benchmarks/gpqa
- AI benchmarks & capabilities epoch.ai https://epoch.ai/benchmarks
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "GPT-6 Astra", https://aurion.semai.id/models/openai-gpt-6-astra/, records of October 2026.