Project AURIONAI Use-Cases Research & Innovation
LLMfamily

GPT-6

OpenAI's GPT-6 family; flagship GPT-6 Astra for complex reasoning and coding, with Sol and Luna tiers.

OpenAI
Levelfamily
ClassLLM
Parametersnot in the notes
Contextnot in the notes
Releasednot in the notes
Opennessproprietary
Runs onnot in the notes
Statusactive

Benchmark Results

vendor-reportedmaintainer-runindependent
ARC-AGI-2knowledge and reasoning
GPT-6 Astra$1.12/taskvendor-reported
95
050100

Score in %. Higher is better.

ARC-AGI-3knowledge and reasoning
GPT-6 Astrawith OpenAI adapter harness (apiyi citing Latent Space)vendor-reported
99.9
GPT-6 AstraConflicting figures across sourcesvendor-reported
98.6
050100

Score in %. Higher is better.

GPT-6 Astradirect, about 63 to 66% (apiyi citing Latent Space)vendor-reported
no score in the notes
Arena Text leaderboardhuman preference arena
GPT-6.1 Solmaxindependent
1,484 ±9
rank 21, Arena Text overall8 Oct 2026 arena.ai
GPT-6 Astramaxindependent
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 overall8 Oct 2026 arena.ai
Arena Vision leaderboardhuman preference arena
GPT-6.1 Solmaxindependent
1,294 ±14
rank 8 of 165, Arena Vision overall, style control default, 165 models9 Oct 2026 arena.ai
GPT-6 Astramaxindependent
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 models9 Oct 2026 arena.ai
GPT-6 Astramax; 52.67 per secondaryindependent
53
rank 7 of 205, AA leaderboard, 205 current models10 Oct 2026 artificialanalysis.ai
GPT-6.1 Solmaxindependent
52
rank 11 of 205, AA leaderboard, 205 current models10 Oct 2026 artificialanalysis.ai
GPT-6 Lunamaxindependent
38
090180

Score in index. Higher is better.

AA leaderboard, 205 current models10 Oct 2026 artificialanalysis.ai
GPT-6 Astravendor-reported
85
benchlm.ai frontier top 69 Oct 2026 benchlm.ai
GPT-6.1 Solestimatedvendor-reported
81.5
090180

Score in index. Higher is better.

benchlm.ai frontier top 69 Oct 2026 benchlm.ai
GPT-6 Astravendor-reported
74.1
050100

Score in %. Higher is better.

GPT-6 AstraEpoch 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 Hub15 Oct 2026 epoch.ai, epoch.ai
GPT-6 Astravendor-reported
97.6
050100

Score in %. Higher is better.

GPT-6 AstraSolved 2 of 68 problemsmaintainer-run
3
050100

Score in %. Higher is better.

Epoch AI Benchmarking Hub3 Sep 2026 epoch.ai
GPQA Diamondknowledge and reasoning
GPT-6 Astravendor-reported
96
050100

Score in %. Higher is better.

rank 1, BenchLM aggregator, top score10 Oct 2026 benchlm.ai
OpenAI MRCR v2long context
GPT-6 Astra512K to 1Mvendor-reported
96.3
050100

Score in %. Higher is better.

OSWorld 2.0agents and tool use
GPT-6 Astravendor-reported
72.6
050100

Score in %. Higher is better.

Terminal-Bench 4.0agents and tool use
GPT-6 Astra57.9% 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

OpenAIGPT-6.1 Sol belongs to this familymultimodal LLM29 Sep 2026
OpenAIGPT-6.1 Astra belongs to this familyLLM28 Sep 2026
OpenAIGPT-6 Luna belongs to this familymultimodal LLM22 Sep 2026
OpenAIGPT-6 Sol belongs to this familymultimodal LLM22 Sep 2026
OpenAIGPT-6 Astra belongs to this familymultimodal LLM3 Sep 2026
Where 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

Developer
OpenAI
Family
not in the notes
Released
– sources
Weights published
–
Record checked
10 Oct 2026
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
not in the notes
Output
not in the notes
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
not in the notes sources
Access routes
not in the notes
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.

Sources

  1. Models | OpenAI API developers.openai.com/api/docs/models https://developers.openai.com/api/docs/models
  2. Models | OpenAI API developers.openai.com/api/docs/models https://developers.openai.com/api/docs/models

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "GPT-6", https://aurion.semai.id/models/openai-gpt-6/, records of October 2026.