Project AURIONAI Use-Cases Research & Innovation
image generation

GPT Image 2

OpenAI image model (gpt-image-2) released Apr 2026, predecessor of GPT Image 2.5.

OpenAIOpenAIUSAGPT ImageFamily
OpenAI
Levelmodel
Classimage generation
Parametersnot in the notes
Contextnot in the notes
ReleasedApr 2026
Opennessproprietary
Runs onnot in the notes
Statusactive

Benchmark Results

independent
Artificial Analysis Text-to-Image Arena AA-Image-T2I v2.0generative media
(high)independent
1,171
5009001,300

Score in Elo; the axis starts at 500, as Elo has no zero. Higher is better.

rank 3, AA Text-to-Image Arena, overall10 Oct 2026 artificialanalysis.ai
LMArena Text-to-Image Arenagenerative media
mediumindependent
1,383 ±4
1,1001,3001,500

Score in Elo; the axis starts at 1,100, as Elo has no zero. Higher is better.

rank 3, LMArena Text-to-Image, overall, updated 7 Oct 20267 Oct 2026 arena.ai
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 Image 1.5 to GPT Image 2: successor, medium confidenceGPT Image 2 to GPT Image 2.5 Flare: successor, high confidenceGPT Image 2 to GPT Image 2.5 Sunburst: successor, high confidenceGPT Image 1.5GPT Image 1.5OpenAI, Dec 2025GPT Image 2GPT Image 2OpenAI, Apr 2026GPT Image 2.5 FlareGPT Image 2.5 FlareOpenAI, Sep 2026GPT Image 2.5 SunburstGPT Image 2.5 SunburstOpenAI, Sep 2026
OpenAIGPT Image 1.5 is the parent (successor)medium confidencenotes
OpenAIGPT Image 2.5 Flare is a child (successor)high confidencenotes
OpenAIGPT Image 2.5 Sunburst is a child (successor)high confidencenotes
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, 4 models. Confidence and evidence are the notes' own.

R&D Topics

Text-to-image foundation models (diffusion and flow transformers)produced by

Identity

Developer
OpenAI
Family
GPT Image
Released
Apr 2026 sourcessecondary report
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
text
Output
image
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
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. GPT-image-2.5 Launches: Flare Is Faster, Sunburst Is Sharper - API易文档中心 docs.apiyi.com https://docs.apiyi.com/en/news/gpt-image-2-5-launch
  2. AA-Image-T2I v2.0 Leaderboard - Top AI Image Models | Artificial Analysis artificialanalysis.ai https://artificialanalysis.ai/text-to-image/arena/leaderboard-text
  3. Text-to-Image Leaderboard: Best AI Image Generators arena.ai https://arena.ai/leaderboard/text-to-image

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "GPT Image 2", https://aurion.semai.id/models/openai-gpt-image-2/, records of October 2026.