Head-to-head comparison

GPT Image 1.5 vs. GPT Image 2.5 Flare

Compare shared capability tests, arena scores with documented retrieval dates, task-specific image pricing, and verified specifications. Research benchmarks, preference arenas, and our n = 1 samples remain separate.

shared result series: 16
shared sample prompts: 4
latest arena retrieval: 2026-10-15

First image modelSecond image model

Specifications and cost

General specifications and task-specific pricing

A model can have one price for generating new images and another for editing. Prices therefore remain tied to the corresponding arena configuration.

Specifications and pricing for GPT Image 1.5 and GPT Image 2.5 Flare
Attribute	GPT Image 1.5	GPT Image 2.5 Flare
Provider	OpenAI	OpenAI
Released	December 2025	September 8, 2026
Access	API, Web app	API
Lifecycle	Marked as deprecated by OpenAI; removed from the API on December 1, 2026 Status source	No separate lifecycle notice
Weights	Proprietary	Proprietary
Parameters	Not published	Not published
Maximum output	1,536 × 1,024 pixels	Not consistently published
Arena configuration	High	No separate configuration named
Text-to-image price	$133 per 1,000 images	$210.7 per 1,000 images
Editing price	$133 per 1,000 images	$210.7 per 1,000 images
Technical source	Model sourceVerified 2026-08-15	Model sourceVerified 2026-09-22

GPT Image 1.5GPT Image 2.5 Flare

Text to Image ArenaUSD per 1,000 images at 1,024 × 1,024 pixels

GPT Image 1.5$133

GPT Image 2.5 Flare$210.7

Image Editing ArenaUSD per 1,000 images at 1,024 × 1,024 pixels

GPT Image 1.5$133

GPT Image 2.5 Flare$210.7

Key to the marks:better valuebetter, but not conclusivetie

Prompt adherence and specialist tests

Shared capability benchmarks

Both checkpoints completed the same four Gradually sample tasks. For each task, 30 archived first outputs are ranked in three differently ordered, model-blind passes. The published 0-100 value normalizes the mean rank. It must still be read as an n = 1 sample per model. No exact shared result from the integrated research benchmarks is available for this pair.

GPT Image 1.5GPT Image 2.5 Flare

Gradually sample test: Typography and layoutMean of three blind ranks across all 30 first outputs, n = 1 each

GPT Image 1.529.9 / 100

GPT Image 2.5 Flare33.3 / 100

Gradually sample test: Product photographyMean of three blind ranks across all 30 first outputs, n = 1 each

GPT Image 1.543.7 / 100

GPT Image 2.5 Flare43.7 / 100

Gradually sample test: Character and detailMean of three blind ranks across all 30 first outputs, n = 1 each

GPT Image 1.577 / 100

GPT Image 2.5 Flare87.3 / 100

Gradually sample test: InfographicMean of three blind ranks across all 30 first outputs, n = 1 each

GPT Image 1.542.5 / 100

GPT Image 2.5 Flare60.9 / 100

Key to the marks:better valuebetter, but not conclusivetie

Capability benchmark scores for GPT Image 1.5 and GPT Image 2.5 Flare
Benchmark	GPT Image 1.5	GPT Image 2.5 Flare
Gradually sample test: Typography and layout	29.9 / 100 Mean rank: 21.33 (23 / 22 / 19) Five rubric scores Headline: 1.67 / 2 Subline: 1.67 / 2 Text control: 1.67 / 2 Visual brief: 1.33 / 2 Layout: 1 / 2	Higher blind-rank score33.3 / 100 Mean rank: 20.33 (21 / 17 / 23) Five rubric scores Headline: 1.67 / 2 Subline: 1.67 / 2 Text control: 1.67 / 2 Visual brief: 1.33 / 2 Layout: 1 / 2
Gradually sample test: Product photography	Tie43.7 / 100 Mean rank: 17.33 (22 / 8 / 22) Five rubric scores Subject: 1.67 / 2 Time: 1 / 2 Watch details: 1.67 / 2 Photography: 1.67 / 2 Exclusions: 1.67 / 2	Tie43.7 / 100 Mean rank: 17.33 (19 / 10 / 23) Five rubric scores Subject: 1.67 / 2 Time: 1.67 / 2 Watch details: 1 / 2 Photography: 1.67 / 2 Exclusions: 1.67 / 2
Gradually sample test: Character and detail	77 / 100 Mean rank: 7.67 (6 / 5 / 12) Five rubric scores Scene: 1 / 2 Wardrobe: 1 / 2 Anatomy: 1 / 2 Props: 1 / 2 Environment: 1 / 2	Higher blind-rank score87.3 / 100 Mean rank: 4.67 (2 / 1 / 11) Five rubric scores Scene: 1 / 2 Wardrobe: 1 / 2 Anatomy: 1 / 2 Props: 1 / 2 Environment: 1 / 2
Gradually sample test: Infographic	42.5 / 100 Mean rank: 17.67 (20 / 14 / 19) Five rubric scores Title: 1.67 / 2 Sequence: 1.67 / 2 Labels: 1 / 2 Diagram: 1.67 / 2 Clarity: 1 / 2	Higher blind-rank score60.9 / 100 Mean rank: 12.33 (12 / 11 / 14) Five rubric scores Title: 1.67 / 2 Sequence: 1.67 / 2 Labels: 1 / 2 Diagram: 1.67 / 2 Clarity: 1 / 2
Key to the marks:better valuebetter, but not conclusivetie

Independent preference tests

Shared arena benchmarks

Artificial Analysis and Arena derive scores from blind comparisons. Raters see outputs for the same prompt and choose the image they prefer. Separate series cover text rendering, photorealism, portraits, art, commercial design, and image editing. Confidence intervals indicate how certain a measured lead is.

12 shared result series

GPT Image 1.5GPT Image 2.5 Flare

Text to Image ArenaBlind preference from the same prompt, higher is better

GPT Image 1.51,102 Elo

GPT Image 2.5 Flare1,190 Elo

Image Editing ArenaBlind preference from the same prompt, higher is better

GPT Image 1.51,103 Elo

GPT Image 2.5 Flare1,161 Elo

LMArena Text to Image: 3D modelingBlind preference from the same prompt, higher is better

GPT Image 1.51,215.587

GPT Image 2.5 Flare1,376.781

LMArena Text to Image: ArtBlind preference from the same prompt, higher is better

GPT Image 1.51,225.428

GPT Image 2.5 Flare1,371.606

LMArena Text to Image: CartoonBlind preference from the same prompt, higher is better

GPT Image 1.51,243.523

GPT Image 2.5 Flare1,420.964

LMArena Text to Image: Commercial designBlind preference from the same prompt, higher is better

GPT Image 1.51,238.795

GPT Image 2.5 Flare1,390.7

LMArena Text to Image: OverallBlind preference from the same prompt, higher is better

GPT Image 1.51,237.366

GPT Image 2.5 Flare1,397.625

LMArena Text to Image: PhotorealismBlind preference from the same prompt, higher is better

GPT Image 1.51,248.33

GPT Image 2.5 Flare1,414.001

LMArena Text to Image: PortraitsBlind preference from the same prompt, higher is better

GPT Image 1.51,261.723

GPT Image 2.5 Flare1,442.351

LMArena Text to Image: Text renderingBlind preference from the same prompt, higher is better

GPT Image 1.51,252.97

GPT Image 2.5 Flare1,432.75

LMArena Image Editing: Multi-image editingBlind preference from the same prompt, higher is better

GPT Image 1.51,343.297

GPT Image 2.5 Flare1,476.312

LMArena Image Editing: OverallBlind preference from the same prompt, higher is better

GPT Image 1.51,369.673

GPT Image 2.5 Flare1,481.016

Key to the marks:better valuebetter, but not conclusivetie

Arena benchmark scores for GPT Image 1.5 and GPT Image 2.5 Flare
Benchmark	GPT Image 1.5	GPT Image 2.5 Flare	Source
Text to Image Arena	1,102 Elo Rank 9, 95% confidence interval: ±9, 14,748 ratings	Higher score1,190 Elo Rank 2, 95% confidence interval: ±9, 12,778 ratings	Artificial AnalysisRetrieved 2026-09-22
Image Editing Arena	1,103 Elo Rank 12, 95% confidence interval: ±9, 12,789 ratings	Higher score1,161 Elo Rank 2, 95% confidence interval: ±8, 17,496 ratings	Artificial AnalysisRetrieved 2026-09-22
LMArena Text to Image: 3D modeling	1,215.587 Rank 17, 95% confidence interval: ±6.34, 17,374 ratings	Higher score1,376.781 Rank 2, 95% confidence interval: ±16.14, 1,609 ratings	LMArenaRetrieved 2026-10-15
LMArena Text to Image: Art	1,225.428 Rank 17, 95% confidence interval: ±5.69, 24,191 ratings	Higher score1,371.606 Rank 2, 95% confidence interval: ±12.79, 2,541 ratings	LMArenaRetrieved 2026-10-15
LMArena Text to Image: Cartoon	1,243.523 Rank 17, 95% confidence interval: ±4.51, 66,223 ratings	Higher score1,420.964 Rank 2, 95% confidence interval: ±10.06, 6,424 ratings	LMArenaRetrieved 2026-10-15
LMArena Text to Image: Commercial design	1,238.795 Rank 17, 95% confidence interval: ±4.42, 65,304 ratings	Higher score1,390.7 Rank 2, 95% confidence interval: ±9.63, 5,620 ratings	LMArenaRetrieved 2026-10-15
LMArena Text to Image: Overall	1,237.366 Rank 17, 95% confidence interval: ±3.06, 169,927 ratings	Higher score1,397.625 Rank 2, 95% confidence interval: ±6.76, 16,889 ratings	LMArenaRetrieved 2026-10-15
LMArena Text to Image: Photorealism	1,248.33 Rank 17, 95% confidence interval: ±4.47, 67,969 ratings	Higher score1,414.001 Rank 2, 95% confidence interval: ±10.15, 5,913 ratings	LMArenaRetrieved 2026-10-15
LMArena Text to Image: Portraits	1,261.723 Rank 14, 95% confidence interval: ±5.57, 33,150 ratings	Higher score1,442.351 Rank 2, 95% confidence interval: ±13.82, 2,725 ratings	LMArenaRetrieved 2026-10-15
LMArena Text to Image: Text rendering	1,252.97 Rank 18, 95% confidence interval: ±4.65, 60,755 ratings	Higher score1,432.75 Rank 2, 95% confidence interval: ±10.12, 5,617 ratings	LMArenaRetrieved 2026-10-15
LMArena Image Editing: Multi-image editing	1,343.297 Rank 12, 95% confidence interval: ±3.36, 228,454 ratings	Higher score1,476.312 Rank 2, 95% confidence interval: ±5.54, 28,778 ratings	LMArenaRetrieved 2026-10-15
LMArena Image Editing: Overall	1,369.673 Rank 17, 95% confidence interval: ±2.59, 654,249 ratings	Higher score1,481.016 Rank 2, 95% confidence interval: ±5.28, 57,408 ratings	LMArenaRetrieved 2026-10-15
Key to the marks:better valuebetter, but not conclusivetie

Visual comparison

Sample images

Our images complement preference data, but do not replace it. The prompt, request count, and selection rule match. Provider resolution, quality tier, randomness, and prompt processing remain visible limitations, so this is not a fully controlled laboratory test.

Largely standardized comparison protocol. Both models receive the same archived prompt, exactly one request, and the first result counts. Files are normalized to 1,024 × 1,024 pixels without cropping. Provider resolution, randomness, quality tier, and prompt processing can still differ. These images are a practical visual test, not a reconstruction of the arena configuration.

Character and detail

Anatomy, clothing, and spatial consistency

Prompt and settings

Create a square cinematic full-body portrait of a fictional bicycle courier waiting under a transparent umbrella at a rainy tram stop in Hamburg at blue hour. She wears a mustard raincoat, navy trousers, red sneakers, a silver helmet, and carries a teal messenger bag. Keep both hands visible, render the bicycle correctly, use realistic wet-street reflections, and include no readable brand names.

GPT Image 1.5. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID openai/gpt-image-1.5, generated Aug 14, 2026, 12:17 PM. Source
GPT Image 2.5 Flare. Provider OpenAI, 1024x1024, quality high, n=1, model ID gpt-image-2.5-flare, generated Sep 28, 2026, 8:53 PM. Source

Protocol gradually-image-comparison-v1, selection rule: first result.

Prompt SHA 256: 985a75b38642a9f0e5e0c0e0c67f1b7f67780d42bd2168fa24e9a7a7a94b0da6

GPT Image 1.5, image SHA 256: 0dff52ccd39400ac66ac8870c9ea937512ff1474688e70118688f420c38c2296

GPT Image 1.5, request SHA 256: 5199631ac6ff07633dd2fb6ab61c918c26e1e02f37e6131828072233ac04527d

GPT Image 2.5 Flare, image SHA 256: 85b17c41b19389cae3ea073ef582e6065a321d741978e772987d22e3ea3e3b08

GPT Image 2.5 Flare, request SHA 256: e1238a1112d45fcc4474ed85f5504be75304152073d5f320d732f5b8c431c759

Infographic

Numbers, labels, and visual organization

Prompt and settings

Create a square German infographic titled SO FUNKTIONIERT PHOTOSYNTHESE. Show exactly four numbered steps in this order: 1 LICHT, 2 WASSER, 3 CO₂, 4 ZUCKER + SAUERSTOFF. Use a clean editorial science style with one plant cross-section, simple arrows, high contrast, legible labels, and no other text.

Protocol gradually-image-comparison-v1, selection rule: first result.

Prompt SHA 256: ed65cb4e6a51e2336f8b149ad4cbb16e020f07d527ad94362e719d2dcf91d94f

GPT Image 1.5, image SHA 256: 1c9ff59c32621c8b48b002dacb0ae66487262280c7c0a5b3d6456c81b248ebe9

GPT Image 1.5, request SHA 256: 7f1efc9531f1e6bed7d61a11c637add9fd892001aea2bb2781f8d89c79a2eb03

GPT Image 2.5 Flare, image SHA 256: bc752abfce1c0d27b73e4084c3e7d82c4c0f71e0e5af97a80f4b24326cc4686e

GPT Image 2.5 Flare, request SHA 256: 8cd44a51b90bec6394d45d678bdfaa16e0fe014a237582999a2370b2e3db1c0b

Product photography

Materials, reflections, and fine details

Prompt and settings

Create a square premium product photograph of a brushed titanium wristwatch standing upright on dark green marble. The watch has a cream dial, thin black hands set to 10:10, twelve distinct hour markers, a realistic crown, and a dark brown leather strap. Soft window light from the left, controlled reflections, shallow depth of field, no text, no logo, no extra objects.

GPT Image 1.5. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID openai/gpt-image-1.5, generated Aug 14, 2026, 12:16 PM. Source
GPT Image 2.5 Flare. Provider OpenAI, 1024x1024, quality high, n=1, model ID gpt-image-2.5-flare, generated Sep 28, 2026, 8:53 PM. Source

Protocol gradually-image-comparison-v1, selection rule: first result.

Prompt SHA 256: c67fd71e91304458a2feef5c91efa8677260fab0c0099a29a2c52cb579f5b2f3

GPT Image 1.5, image SHA 256: 67cfa2f324447027ceb5f82e9446d40a1395b46ce425890a74606b4d97731cf6

GPT Image 1.5, request SHA 256: c850843a298631a4076c5d2686de8e9d7223534f2b8ca53505f437862718bef9

GPT Image 2.5 Flare, image SHA 256: 69fedb7d635d1329c461ff1ee9e5cf8384119e218e3b3bdb93b9e11f728335d8

GPT Image 2.5 Flare, request SHA 256: a305103045fa5c2ede55b612333ab07c44dc0128f3d2faec67b8a117e52a82f0

Typography and layout

Legible text, hierarchy, and composition

Prompt and settings

Create a square editorial poster for an imaginary night train called MONDFALTER. Show the exact German headline MONDFALTER and the exact subline BERLIN NACH LISSABON. Use a restrained midnight-blue and warm-cream palette, one stylized moth, strong Swiss-grid typography, generous negative space, and no additional words or logos.

GPT Image 1.5. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID openai/gpt-image-1.5, generated Aug 14, 2026, 1:59 PM. Source
GPT Image 2.5 Flare. Provider OpenAI, 1024x1024, quality high, n=1, model ID gpt-image-2.5-flare, generated Sep 28, 2026, 8:52 PM. Source

Protocol gradually-image-comparison-v1, selection rule: first result.

Prompt SHA 256: 2e012c3d14ee5dd02203a94f394ca80a5038cdebd6032b25a8b8a221f2255419

GPT Image 1.5, image SHA 256: 6a4cec86850fd371b65274198e2bf630b3cf36a096f9fb953d4bfe17c3222ebe

GPT Image 1.5, request SHA 256: 9c3a396aecfcaae3f8a25edbe5c8c44d0d33199d7ba29efda864d2b0221c3250

GPT Image 2.5 Flare, image SHA 256: cc90d54a99e1bad9e0cc8e4196746fb1d56a2fdd2a9ee101dbbf270ef5e4b6a8

GPT Image 2.5 Flare, request SHA 256: ec1fe63f04c319c731a93750e3d864df87e3f36142b33d88a3e1b5c5971aa2a5

How to read this comparison

An Elo score is not a verdict on creativity

A higher arena score means this specific configuration was preferred more often in blind comparisons.

Typography, character consistency, local execution, licensing, and price may matter more to your workload than overall visual appeal.

Prices cover 1,000 images at 1,024 × 1,024 pixels using settings documented by Artificial Analysis. Subscriptions and special rates are excluded.

More matchups

Compare GPT Image 1.5 and GPT Image 2.5 Flare with other important image models under the same evidence rules. Each page shows only exact shared measurements and samples.

View the complete image model comparison

GPT Image 1.5 vs. GPT Image 2.5 Flare

Change image model selection

General specifications and task-specific pricing

Shared capability benchmarks

Shared arena benchmarks

Sample images

Character and detail

Infographic

Product photography

Typography and layout

An Elo score is not a verdict on creativity

Related image model comparisons