Head-to-head comparison

MAI-Image-2.5 vs. Krea 2 Large

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: 13
shared sample prompts: 4
latest arena retrieval: 2026-09-22

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 MAI-Image-2.5 and Krea 2 Large
Attribute	MAI-Image-2.5	Krea 2 Large
Provider	Microsoft AI	Krea
Released	June 2026	May 2026
Access	API, Web app	API, Web app
Lifecycle	Preview in Microsoft Foundry Status source	No separate lifecycle notice
Weights	Proprietary	Proprietary
Parameters	20 billion	Not published
Maximum output	1,048,576 pixels	1K
Arena configuration	No separate configuration named	Large
Text-to-image price	$48.1 per 1,000 images	$60 per 1,000 images
Editing price	$48.1 per 1,000 images	No arena entry
Technical source	Model sourceVerified 2026-08-15	Model sourceVerified 2026-08-15

MAI-Image-2.5Krea 2 Large

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

MAI-Image-2.5$48.1

Krea 2 Large$60

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.

MAI-Image-2.5Krea 2 Large

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

MAI-Image-2.582.8 / 100

Krea 2 Large74.7 / 100

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

MAI-Image-2.579.3 / 100

Krea 2 Large81.6 / 100

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

MAI-Image-2.520.7 / 100

Krea 2 Large56.3 / 100

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

MAI-Image-2.564.4 / 100

Krea 2 Large89.7 / 100

Key to the marks:better valuebetter, but not conclusivetie

Capability benchmark scores for MAI-Image-2.5 and Krea 2 Large
Benchmark	MAI-Image-2.5	Krea 2 Large
Gradually sample test: Typography and layout	Higher blind-rank score82.8 / 100 Mean rank: 6 (3 / 7 / 8) Five rubric scores Headline: 1.67 / 2 Subline: 1.67 / 2 Text control: 1.67 / 2 Visual brief: 1.67 / 2 Layout: 1.67 / 2	74.7 / 100 Mean rank: 8.33 (14 / 2 / 9) Five rubric scores Headline: 1.67 / 2 Subline: 1.67 / 2 Text control: 1.67 / 2 Visual brief: 1.67 / 2 Layout: 1.33 / 2
Gradually sample test: Product photography	79.3 / 100 Mean rank: 7 (6 / 12 / 3) Five rubric scores Subject: 1.67 / 2 Time: 1.67 / 2 Watch details: 1.67 / 2 Photography: 1.67 / 2 Exclusions: 1.67 / 2	Higher blind-rank score81.6 / 100 Mean rank: 6.33 (5 / 5 / 9) Five rubric scores Subject: 1.67 / 2 Time: 1.67 / 2 Watch details: 1.67 / 2 Photography: 1.67 / 2 Exclusions: 1.67 / 2
Gradually sample test: Character and detail	20.7 / 100 Mean rank: 24 (24 / 21 / 27) Five rubric scores Scene: 1 / 2 Wardrobe: 1 / 2 Anatomy: 1 / 2 Props: 1 / 2 Environment: 1 / 2	Higher blind-rank score56.3 / 100 Mean rank: 13.67 (11 / 7 / 23) Five rubric scores Scene: 1 / 2 Wardrobe: 1 / 2 Anatomy: 1 / 2 Props: 1 / 2 Environment: 1 / 2
Gradually sample test: Infographic	64.4 / 100 Mean rank: 11.33 (11 / 12 / 11) Five rubric scores Title: 1.67 / 2 Sequence: 1.33 / 2 Labels: 1 / 2 Diagram: 1.67 / 2 Clarity: 1.33 / 2	Higher blind-rank score89.7 / 100 Mean rank: 4 (5 / 4 / 3) Five rubric scores Title: 1.67 / 2 Sequence: 1.67 / 2 Labels: 1.67 / 2 Diagram: 1.67 / 2 Clarity: 1.67 / 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.

9 shared result series

MAI-Image-2.5Krea 2 Large

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

MAI-Image-2.51,103 Elo

Krea 2 Large1,023 Elo

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

MAI-Image-2.51,248.552

Krea 2 Large1,115.555

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

MAI-Image-2.51,277.455

Krea 2 Large1,115.68

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

MAI-Image-2.51,269.579

Krea 2 Large1,112.783

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

MAI-Image-2.51,260.92

Krea 2 Large1,105.604

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

MAI-Image-2.51,254.072

Krea 2 Large1,108.262

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

MAI-Image-2.51,250.943

Krea 2 Large1,123.298

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

MAI-Image-2.51,257.755

Krea 2 Large1,118.338

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

MAI-Image-2.51,282.526

Krea 2 Large1,111.574

Key to the marks:better valuebetter, but not conclusivetie

Arena benchmark scores for MAI-Image-2.5 and Krea 2 Large
Benchmark	MAI-Image-2.5	Krea 2 Large	Source
Text to Image Arena	Higher score1,103 Elo Rank 8, 95% confidence interval: ±9, 14,914 ratings	1,023 Elo Rank 22, 95% confidence interval: ±7, 15,332 ratings	Artificial AnalysisRetrieved 2026-09-22
LMArena Text to Image: 3D modeling	Higher score1,248.552 Rank 11, 95% confidence interval: ±9.04, 5,230 ratings	1,115.555 Rank 47, 95% confidence interval: ±10.09, 3,625 ratings	LMArenaRetrieved 2026-09-19
LMArena Text to Image: Art	Higher score1,277.455 Rank 7, 95% confidence interval: ±7.76, 8,400 ratings	1,115.68 Rank 47, 95% confidence interval: ±8.55, 5,894 ratings	LMArenaRetrieved 2026-09-19
LMArena Text to Image: Cartoon	Higher score1,269.579 Rank 11, 95% confidence interval: ±5.93, 22,528 ratings	1,112.783 Rank 47, 95% confidence interval: ±6.67, 15,491 ratings	LMArenaRetrieved 2026-09-19
LMArena Text to Image: Commercial design	Higher score1,260.92 Rank 10, 95% confidence interval: ±5.97, 20,864 ratings	1,105.604 Rank 53, 95% confidence interval: ±6.48, 13,623 ratings	LMArenaRetrieved 2026-09-19
LMArena Text to Image: Overall	Higher score1,254.072 Rank 12, 95% confidence interval: ±4.28, 57,250 ratings	1,108.262 Rank 51, 95% confidence interval: ±4.53, 39,614 ratings	LMArenaRetrieved 2026-09-19
LMArena Text to Image: Photorealism	Higher score1,250.943 Rank 14, 95% confidence interval: ±5.89, 21,971 ratings	1,123.298 Rank 44, 95% confidence interval: ±6.65, 15,239 ratings	LMArenaRetrieved 2026-09-19
LMArena Text to Image: Portraits	Higher score1,257.755 Rank 13, 95% confidence interval: ±7.1, 10,873 ratings	1,118.338 Rank 49, 95% confidence interval: ±8.13, 7,529 ratings	LMArenaRetrieved 2026-09-19
LMArena Text to Image: Text rendering	Higher score1,282.526 Rank 11, 95% confidence interval: ±6.17, 19,611 ratings	1,111.574 Rank 50, 95% confidence interval: ±6.66, 12,920 ratings	LMArenaRetrieved 2026-09-19
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.

MAI-Image-2.5. Provider OpenRouter, aspect ratio 1:1, provider default 1K resolution, n=1, seed=provider random, actual cost $0.048508, model ID microsoft/mai-image-2.5, generated Aug 14, 2026, 1:26 PM. Source
Krea 2 Large. Provider OpenRouter, aspect ratio 1:1, resolution 1K, n=1, seed=provider random, actual cost $0.060000, model ID krea/krea-2-large, generated Aug 14, 2026, 1:36 PM. Source

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

Prompt SHA 256: 985a75b38642a9f0e5e0c0e0c67f1b7f67780d42bd2168fa24e9a7a7a94b0da6

MAI-Image-2.5, image SHA 256: ca1c58688ae4601975d7e1f7b58bb43a0a999e736f610d9f51cd11e06284bced

MAI-Image-2.5, request SHA 256: 40fc54cbcee64f9045c44e702e013b649a0d8bbd7f8e2390d839bc38ee183b90

Krea 2 Large, image SHA 256: 0ff58bb2381d2d753ef76973ac739c5aa556d182192ebb8d6f44ccba0898f991

Krea 2 Large, request SHA 256: fae1cc0200a63e9c6276495a04efa321455adc787e860774a9512fd08af0ab67

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.

MAI-Image-2.5. Provider OpenRouter, aspect ratio 1:1, provider default 1K resolution, n=1, seed=provider random, actual cost $0.048538, model ID microsoft/mai-image-2.5, generated Aug 14, 2026, 1:26 PM. Source
Krea 2 Large. Provider OpenRouter, aspect ratio 1:1, resolution 1K, n=1, seed=provider random, actual cost $0.060000, model ID krea/krea-2-large, generated Aug 14, 2026, 1:37 PM. Source

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

Prompt SHA 256: ed65cb4e6a51e2336f8b149ad4cbb16e020f07d527ad94362e719d2dcf91d94f

MAI-Image-2.5, image SHA 256: eaf00a906231e8859f98ef5dc2cce7e8017797819aea453305a4ef0e970d4dbf

MAI-Image-2.5, request SHA 256: bbedc701e9933a8d6ed0fbb2a6fbb7214214fad9d32d9ae80a114a7254a0bcf1

Krea 2 Large, image SHA 256: 5b489d9f70c7253124a51d313bfaea1606f1b6c53ef19d238b5aa9601d2ea6ef

Krea 2 Large, request SHA 256: 6f885a262985589a70b17bb0eec66f0d7cba9125e03eb7c7f56166bef2c03ebe

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.

MAI-Image-2.5. Provider OpenRouter, aspect ratio 1:1, provider default 1K resolution, n=1, seed=provider random, actual cost $0.048513, model ID microsoft/mai-image-2.5, generated Aug 14, 2026, 1:25 PM. Source
Krea 2 Large. Provider OpenRouter, aspect ratio 1:1, resolution 1K, n=1, seed=provider random, actual cost $0.060000, model ID krea/krea-2-large, generated Aug 14, 2026, 1:36 PM. Source

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

Prompt SHA 256: c67fd71e91304458a2feef5c91efa8677260fab0c0099a29a2c52cb579f5b2f3

MAI-Image-2.5, image SHA 256: 67d4930b711fac61482231c4bc270cfcdb41c1b0daf653045781fb2126e237dd

MAI-Image-2.5, request SHA 256: 071e156eeb3e65e6744b7c6b675ffcb32b551dcfc1033a55e30e9561c0bd78a9

Krea 2 Large, image SHA 256: d4d912904708c24aae1059d5096a11fcb0b78f5be48be2b045ea07ca046914c8

Krea 2 Large, request SHA 256: 963a3b3dc2b747d7dd0ce49965cff94ed16bf9461d4335b255ae547ce4b9f19b

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.

MAI-Image-2.5. Provider OpenRouter, aspect ratio 1:1, provider default 1K resolution, n=1, seed=provider random, actual cost $0.048473, model ID microsoft/mai-image-2.5, generated Aug 14, 2026, 2:03 PM. Source
Krea 2 Large. Provider OpenRouter, aspect ratio 1:1, resolution 1K, n=1, seed=provider random, actual cost $0.060000, model ID krea/krea-2-large, generated Aug 14, 2026, 2:05 PM. Source

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

Prompt SHA 256: 2e012c3d14ee5dd02203a94f394ca80a5038cdebd6032b25a8b8a221f2255419

MAI-Image-2.5, image SHA 256: 4c8a60555b57b8c3b5ebaa131371d1bba9d31bfafe7aaa772554969f7c28cb08

MAI-Image-2.5, request SHA 256: f14577273bd6b0980f49e13988b01555bb55dc824317b201b5fab3d2ef72e666

Krea 2 Large, image SHA 256: f34eb736928ed7555e35c096f9da4ab2df41ba8880e54fdf7cd8b3dce6f3480d

Krea 2 Large, request SHA 256: faa085c9c08ab67ae3e0c9524c4053c2b3bafd9d73635a9e967be4e4ecf08619

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 MAI-Image-2.5 and Krea 2 Large 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

MAI-Image-2.5 vs. Krea 2 Large

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