Skip to main content

GPT Image 1.5vs.MAI-Image-2.5

Which one is better?

In our own test both are on par. In the arena, MAI-Image-2.5 leads. GPT Image 1.5 costs 2.8 times as much per image.

Test images

Same task, the first image of each. The task with the biggest difference is preselected.

GPT Image 1.5: Character and detail, first image from the fixed test run
GPT Image 1.589 out of 100
MAI-Image-2.5: Character and detail, first image from the fixed test run
MAI-Image-2.555 out of 100

Result for “Character and detail”:GPT Image 1.5 slightly ahead

Prompt given to both modelsCreate 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.

What the rating looks at: Anatomy, clothing, and spatial consistency.

“Ahead”: better in all three rating rounds. “Slightly ahead”: a higher value, but not in every round.

Test protocol of the images

Each test attempt uses the same archived prompt and one request. The first output of that attempt counts. Repeats after technical test failures are disclosed for the affected images. Files are normalized to 1,024 × 1,024 pixels without cropping. Provider resolution, randomness, quality tier and prompt processing can still differ. The images are a practical visual test, not a reconstruction of the arena configuration.

Character and detail

GPT Image 1.5: together, 1024x1024, n=1, seed=provider random, provider default steps, generated Aug 14, 2026, 12:17 PM. Source

MAI-Image-2.5: openrouter, aspect ratio 1:1, provider default 1K resolution, n=1, seed=provider random, actual cost $0.048508, generated Aug 14, 2026, 1:26 PM. Source

Protocol gradually-image-comparison-v1. Prompt SHA 256: 985a75b38642a9f0e5e0c0e0c67f1b7f67780d42bd2168fa24e9a7a7a94b0da6

GPT Image 1.5 image SHA 256: 0dff52ccd39400ac66ac8870c9ea937512ff1474688e70118688f420c38c2296

MAI-Image-2.5 image SHA 256: ca1c58688ae4601975d7e1f7b58bb43a0a999e736f610d9f51cd11e06284bced

Infographic

GPT Image 1.5: together, 1024x1024, n=1, seed=provider random, provider default steps, generated Aug 14, 2026, 12:17 PM. Source

MAI-Image-2.5: openrouter, aspect ratio 1:1, provider default 1K resolution, n=1, seed=provider random, actual cost $0.048538, generated Aug 14, 2026, 1:26 PM. Source

Protocol gradually-image-comparison-v1. Prompt SHA 256: ed65cb4e6a51e2336f8b149ad4cbb16e020f07d527ad94362e719d2dcf91d94f

GPT Image 1.5 image SHA 256: 1c9ff59c32621c8b48b002dacb0ae66487262280c7c0a5b3d6456c81b248ebe9

MAI-Image-2.5 image SHA 256: eaf00a906231e8859f98ef5dc2cce7e8017797819aea453305a4ef0e970d4dbf

Product photography

GPT Image 1.5: together, 1024x1024, n=1, seed=provider random, provider default steps, generated Aug 14, 2026, 12:16 PM. Source

MAI-Image-2.5: openrouter, aspect ratio 1:1, provider default 1K resolution, n=1, seed=provider random, actual cost $0.048513, generated Aug 14, 2026, 1:25 PM. Source

Protocol gradually-image-comparison-v1. Prompt SHA 256: c67fd71e91304458a2feef5c91efa8677260fab0c0099a29a2c52cb579f5b2f3

GPT Image 1.5 image SHA 256: 67cfa2f324447027ceb5f82e9446d40a1395b46ce425890a74606b4d97731cf6

MAI-Image-2.5 image SHA 256: 67d4930b711fac61482231c4bc270cfcdb41c1b0daf653045781fb2126e237dd

Typography and layout

GPT Image 1.5: together, 1024x1024, n=1, seed=provider random, provider default steps, generated Aug 14, 2026, 1:59 PM. Source

MAI-Image-2.5: openrouter, aspect ratio 1:1, provider default 1K resolution, n=1, seed=provider random, actual cost $0.048473, generated Aug 14, 2026, 2:03 PM. Source

Protocol gradually-image-comparison-v1. Prompt SHA 256: 2e012c3d14ee5dd02203a94f394ca80a5038cdebd6032b25a8b8a221f2255419

GPT Image 1.5 image SHA 256: 6a4cec86850fd371b65274198e2bf630b3cf36a096f9fb953d4bfe17c3222ebe

MAI-Image-2.5 image SHA 256: 4c8a60555b57b8c3b5ebaa131371d1bba9d31bfafe7aaa772554969f7c28cb08

The numbers at a glance

Arena ratingfrom votes by users · higher is better
1,236

GPT Image 1.5

Rank 13 of 21

1,253

MAI-Image-2.5

Rank 9 of 21

GraduallyBenchour own rating, 0 to 100 · higher is better
68

GPT Image 1.5

Rank 29 of 108

69

MAI-Image-2.5

Rank 26 of 108

Price per imagedollars through the API · lower is better
$0.13

GPT Image 1.5

expensive

$0.048

MAI-Image-2.5

fairly cheap

Ranks among the 21 image models with an arena rating and the 108 with a GraduallyBench run; prices compared with 28 models with an API price.

GPT Image 1.5

Subscription
No OpenAI subscription includes this model. Through other providers from ≈ €6.36 a month (ElevenLabs Starter, with limited credits). 42 plans in Germany.
Via API
$0.13 per image, 100 images $13.30.

MAI-Image-2.5

Subscription
No Microsoft AI subscription includes this model. Through other providers from €19.04 a month (Magnific Premium, with limited credits). 6 plans in Germany.
Via API
$0.048 per image, 100 images $4.81.

Subscriptions only count plans that name exactly this model. Subscription prices include VAT, API prices are in dollars.

Arena rating (LMArena) from Nov 6, 2026 · GraduallyBench from Nov 3, 2026 · API prices from Nov 6, 2026 · Subscription database from Sep 29, 2026 (38 days old)

All data side by side

The better value is bold. For ratings only when the gap is clear.

KennzahlGPT Image 1.5MAI-Image-2.5
Ratings
Arena ratingfrom votes by users, higher is better1,2361,253
Arena rankRank 13 of 21Rank 9 of 21
Arena votesmore votes, a safer rating173,79861,222
GraduallyBenchour own rating, 0 to 1006869
GraduallyBench by task
Typography and layoutLegible text, hierarchy, and composition6082
Product photographyMaterials, reflections, and fine details5270
Character and detailAnatomy, clothing, and spatial consistency8955
InfographicNumbers, labels, and visual organization7269
API price
Per imagelower is better$0.13$0.048
100 images$13.30$4.81
Profile
ReleasedDecember 2025June 2026
Weightsopen means: runs locallyproprietaryproprietary
LifecycleMarked as deprecated by OpenAI; removed from the API on December 1, 2026Preview in Microsoft Foundry
AccessAPI, Web appAPI, Web app
Parametersnot published20 billion
Largest output1,536 × 1,024 pixels1,048,576 pixels
Plans in Germanynaming exactly this model426

API prices for one image at 1,024 × 1,024 pixels according to Artificial Analysis.

Sources: GPT Image 1.5 model source, status source (verified Aug 15, 2026) · MAI-Image-2.5 model source, status source (verified Aug 15, 2026)

Arena ratings by category

From blind votes on LMArena. “Ahead” means the lead is clear.

Arena rating per categoryfrom votes by users · higher is betterGPT Image 1.5MAI-Image-2.5
Text to Image ArenaGPT Image 1.5: 1,124MAI-Image-2.5: 1,120level
Image Editing ArenaGPT Image 1.5: 1,116MAI-Image-2.5: 1,124level
Text to Image: 3D modelingGPT Image 1.5: 1,218MAI-Image-2.5: 1,251MAI-Image-2.5 ahead
Text to Image: ArtGPT Image 1.5: 1,225MAI-Image-2.5: 1,277MAI-Image-2.5 ahead
Text to Image: CartoonGPT Image 1.5: 1,244MAI-Image-2.5: 1,269MAI-Image-2.5 ahead
Text to Image: Commercial designGPT Image 1.5: 1,238MAI-Image-2.5: 1,259MAI-Image-2.5 ahead
Text to Image: OverallGPT Image 1.5: 1,236MAI-Image-2.5: 1,253MAI-Image-2.5 ahead
Text to Image: PhotorealismGPT Image 1.5: 1,247MAI-Image-2.5: 1,251level
Text to Image: PortraitsGPT Image 1.5: 1,259MAI-Image-2.5: 1,255level
Text to Image: Text renderingGPT Image 1.5: 1,251MAI-Image-2.5: 1,281MAI-Image-2.5 ahead
Image Editing: OverallGPT Image 1.5: 1,368MAI-Image-2.5: 1,400MAI-Image-2.5 ahead

Artificial Analysis from Nov 6, 2026 · LMArena from Nov 6, 2026

All individual values with sources
RatingGPT Image 1.5MAI-Image-2.5Source
Text to Image Arena1,1241,120Artificial AnalysisRetrieved Nov 6, 2026
Image Editing Arena1,1161,124Artificial AnalysisRetrieved Nov 6, 2026
Text to Image: 3D modeling1,2181,251LMArenaRetrieved Nov 6, 2026
Text to Image: Art1,2251,277LMArenaRetrieved Nov 6, 2026
Text to Image: Cartoon1,2441,269LMArenaRetrieved Nov 6, 2026
Text to Image: Commercial design1,2381,259LMArenaRetrieved Nov 6, 2026
Text to Image: Overall1,2361,253LMArenaRetrieved Nov 6, 2026
Text to Image: Photorealism1,2471,251LMArenaRetrieved Nov 6, 2026
Text to Image: Portraits1,2591,255LMArenaRetrieved Nov 6, 2026
Text to Image: Text rendering1,2511,281LMArenaRetrieved Nov 6, 2026
Image Editing: Overall1,3681,400LMArenaRetrieved Nov 6, 2026

More comparisons

Compare GPT Image 1.5 and MAI-Image-2.5 with the models people compare them with most often.

Compare another matchup