Head-to-head comparison

Nano Banana 2 vs. MAI-Image-2.5

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: 15
shared sample prompts: 4
latest arena retrieval: 2026-08-26

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 Nano Banana 2 and MAI-Image-2.5
Attribute	Nano Banana 2	MAI-Image-2.5
Provider	Google	Microsoft AI
Released	February 2026	June 2026
Access	API, Web app	API, Web app
Lifecycle	Stable API since May 28, 2026. The arena entry names the earlier preview configuration Status source	Preview in Microsoft Foundry Status source
Weights	Proprietary	Proprietary
Parameters	Not published	20 billion
Maximum output	4K	1,048,576 pixels
Arena configuration	Gemini 3.1 Flash Image Preview	No separate configuration named
Text-to-image price	$67 per 1,000 images	$48.1 per 1,000 images
Editing price	$67 per 1,000 images	$48.1 per 1,000 images
Technical source	Model sourceVerified 2026-08-15	Model sourceVerified 2026-08-15

Nano Banana 2MAI-Image-2.5

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

Nano Banana 2$67

MAI-Image-2.5$48.1

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

Nano Banana 2$67

MAI-Image-2.5$48.1

Key to the marks:better valuebetter, but not conclusivetie

Prompt adherence and specialist tests

Shared capability benchmarks

Every matchup includes the same four Gradually sample tasks. For each task, one archived first output from every model is 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.

Nano Banana 2MAI-Image-2.5

Gradually sample test: Typography and layoutMean of three blind ranks across all 28 first outputs, n = 1 each

Nano Banana 286.4 / 100

MAI-Image-2.593.8 / 100

Gradually sample test: Product photographyMean of three blind ranks across all 28 first outputs, n = 1 each

Nano Banana 229.6 / 100

MAI-Image-2.586.4 / 100

Gradually sample test: Character and detailMean of three blind ranks across all 28 first outputs, n = 1 each

Nano Banana 218.5 / 100

MAI-Image-2.524.7 / 100

Gradually sample test: InfographicMean of three blind ranks across all 28 first outputs, n = 1 each

Nano Banana 249.4 / 100

MAI-Image-2.565.4 / 100

Key to the marks:better valuebetter, but not conclusivetie

Capability benchmark scores for Nano Banana 2 and MAI-Image-2.5
Benchmark	Nano Banana 2	MAI-Image-2.5
Gradually sample test: Typography and layout	86.4 / 100 Mean rank: 4.67 (8 / 2 / 4) Five rubric scores Headline: 1.67 / 2 Subline: 1.67 / 2 Text control: 1.67 / 2 Visual brief: 1.33 / 2 Layout: 1.33 / 2	Higher blind-rank score93.8 / 100 Mean rank: 2.67 (2 / 3 / 3) Five rubric scores Headline: 1.67 / 2 Subline: 1.67 / 2 Text control: 1.67 / 2 Visual brief: 1.33 / 2 Layout: 1.33 / 2
Gradually sample test: Product photography	29.6 / 100 Mean rank: 20 (24 / 17 / 19) Five rubric scores Subject: 1.33 / 2 Time: 1.33 / 2 Watch details: 1.33 / 2 Photography: 1.33 / 2 Exclusions: 1 / 2	Higher blind-rank score86.4 / 100 Mean rank: 4.67 (1 / 5 / 8) Five rubric scores Subject: 1.33 / 2 Time: 1.33 / 2 Watch details: 1.33 / 2 Photography: 1.33 / 2 Exclusions: 1.33 / 2
Gradually sample test: Character and detail	18.5 / 100 Mean rank: 23 (24 / 18 / 27) Five rubric scores Scene: 1.33 / 2 Wardrobe: 1.33 / 2 Anatomy: 1 / 2 Props: 0.67 / 2 Environment: 0.67 / 2	Higher blind-rank score24.7 / 100 Mean rank: 21.33 (21 / 21 / 22) Five rubric scores Scene: 1.33 / 2 Wardrobe: 1 / 2 Anatomy: 1 / 2 Props: 0.33 / 2 Environment: 1.33 / 2
Gradually sample test: Infographic	49.4 / 100 Mean rank: 14.67 (16 / 14 / 14) Five rubric scores Title: 1.67 / 2 Sequence: 1 / 2 Labels: 1 / 2 Diagram: 1.67 / 2 Clarity: 1 / 2	Higher blind-rank score65.4 / 100 Mean rank: 10.33 (11 / 10 / 10) Five rubric scores Title: 1.67 / 2 Sequence: 1 / 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.

11 shared result series

Nano Banana 2MAI-Image-2.5

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

Nano Banana 21,321 Elo

MAI-Image-2.51,303 Elo

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

Nano Banana 21,250 Elo

MAI-Image-2.51,257 Elo

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

Nano Banana 21,258.705

MAI-Image-2.51,246.107

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

Nano Banana 21,250.508

MAI-Image-2.51,277.636

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

Nano Banana 21,266.735

MAI-Image-2.51,270.066

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

Nano Banana 21,272.164

MAI-Image-2.51,260.487

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

Nano Banana 21,263.056

MAI-Image-2.51,256.13

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

Nano Banana 21,269.812

MAI-Image-2.51,253.013

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

Nano Banana 21,266.805

MAI-Image-2.51,259.199

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

Nano Banana 21,294.784

MAI-Image-2.51,282.791

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

Nano Banana 21,386.267

MAI-Image-2.51,401.279

Key to the marks:better valuebetter, but not conclusivetie

Arena benchmark scores for Nano Banana 2 and MAI-Image-2.5
Benchmark	Nano Banana 2	MAI-Image-2.5	Source
Text to Image Arena	No clear lead1,321 Elo Rank 4, 95% confidence interval: ±9, 15,335 ratings	1,303 Elo Rank 6, 95% confidence interval: ±9, 14,800 ratings	Artificial AnalysisRetrieved 2026-08-26
Image Editing Arena	1,250 Elo Rank 7, 95% confidence interval: ±7, 12,690 ratings	No clear lead1,257 Elo Rank 4, 95% confidence interval: ±8, 11,305 ratings	Artificial AnalysisRetrieved 2026-08-26
LMArena Text to Image: 3D modeling	No clear lead1,258.705 Rank 3, 95% confidence interval: ±11.62, 2,907 ratings	1,246.107 Rank 5, 95% confidence interval: ±9.6, 4,252 ratings	LMArenaRetrieved 2026-08-26
LMArena Text to Image: Art	1,250.508 Rank 8, 95% confidence interval: ±9.92, 4,154 ratings	Higher score1,277.636 Rank 3, 95% confidence interval: ±8.37, 6,571 ratings	LMArenaRetrieved 2026-08-26
LMArena Text to Image: Cartoon	1,266.735 Rank 8, 95% confidence interval: ±7.6, 10,445 ratings	No clear lead1,270.066 Rank 7, 95% confidence interval: ±6.37, 17,440 ratings	LMArenaRetrieved 2026-08-26
LMArena Text to Image: Commercial design	No clear lead1,272.164 Rank 4, 95% confidence interval: ±7.4, 10,316 ratings	1,260.487 Rank 6, 95% confidence interval: ±6.3, 17,261 ratings	LMArenaRetrieved 2026-08-26
LMArena Text to Image: Overall	No clear lead1,263.056 Rank 5, 95% confidence interval: ±5.24, 27,910 ratings	1,256.13 Rank 8, 95% confidence interval: ±4.57, 44,940 ratings	LMArenaRetrieved 2026-08-26
LMArena Text to Image: Photorealism	Higher score1,269.812 Rank 6, 95% confidence interval: ±7.28, 11,229 ratings	1,253.013 Rank 10, 95% confidence interval: ±6.3, 17,468 ratings	LMArenaRetrieved 2026-08-26
LMArena Text to Image: Portraits	No clear lead1,266.805 Rank 7, 95% confidence interval: ±9.15, 5,554 ratings	1,259.199 Rank 10, 95% confidence interval: ±7.61, 8,541 ratings	LMArenaRetrieved 2026-08-26
LMArena Text to Image: Text rendering	No clear lead1,294.784 Rank 5, 95% confidence interval: ±7.73, 9,489 ratings	1,282.791 Rank 7, 95% confidence interval: ±6.6, 15,799 ratings	LMArenaRetrieved 2026-08-26
LMArena Image Editing: Overall	1,386.267 Rank 10, 95% confidence interval: ±3.71, 117,943 ratings	Higher score1,401.279 Rank 5, 95% confidence interval: ±3.56, 170,301 ratings	LMArenaRetrieved 2026-08-26
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.

Nano Banana 2. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID google/flash-image-3.1, generated Aug 14, 2026, 12:15 PM. Source
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

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

Prompt SHA 256: 985a75b38642a9f0e5e0c0e0c67f1b7f67780d42bd2168fa24e9a7a7a94b0da6

Nano Banana 2, image SHA 256: 5d3a70ed3fe3328484725565d9c91fb25fc7f745bd66872dae432444493a83de

Nano Banana 2, request SHA 256: 406e70dda817fa504900359d5c374ebb06fc8ea29f34c8a15f630e9a10489aec

MAI-Image-2.5, image SHA 256: ca1c58688ae4601975d7e1f7b58bb43a0a999e736f610d9f51cd11e06284bced

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

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.

Nano Banana 2. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID google/flash-image-3.1, generated Aug 14, 2026, 12:15 PM. Source
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

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

Prompt SHA 256: ed65cb4e6a51e2336f8b149ad4cbb16e020f07d527ad94362e719d2dcf91d94f

Nano Banana 2, image SHA 256: 66123dd4e8cd5d22ecdca9cca8e4c5853a8046370aa4861ffee807a8c122c769

Nano Banana 2, request SHA 256: 10e973caab6f314ec731d9d377b19f5d51f279e9e2962133c49682bfbba3fe3d

MAI-Image-2.5, image SHA 256: eaf00a906231e8859f98ef5dc2cce7e8017797819aea453305a4ef0e970d4dbf

MAI-Image-2.5, request SHA 256: bbedc701e9933a8d6ed0fbb2a6fbb7214214fad9d32d9ae80a114a7254a0bcf1

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.

Nano Banana 2. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID google/flash-image-3.1, generated Aug 14, 2026, 12:15 PM. Source
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

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

Prompt SHA 256: c67fd71e91304458a2feef5c91efa8677260fab0c0099a29a2c52cb579f5b2f3

Nano Banana 2, image SHA 256: 509871921c450f6f07ec28f91a380992db1b3017108fd5928fe0aa9670a1ecdc

Nano Banana 2, request SHA 256: 631ce921c9772c7c2109900c8662471564a871def8e70f50ce29ce83ab71daab

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

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

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.

Nano Banana 2. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID google/flash-image-3.1, generated Aug 14, 2026, 1:59 PM. Source
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

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

Prompt SHA 256: 2e012c3d14ee5dd02203a94f394ca80a5038cdebd6032b25a8b8a221f2255419

Nano Banana 2, image SHA 256: 06ae79c07d1604d3da3bbfa80bac73ac15c88af5cb8c013faaf5c9ea93092305

Nano Banana 2, request SHA 256: 6f1909c093d741b97bc2b4fe76e889009776dbe8635d2a14dbedd89bb4cae8fb

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

MAI-Image-2.5, request SHA 256: f14577273bd6b0980f49e13988b01555bb55dc824317b201b5fab3d2ef72e666

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 Nano Banana 2 and MAI-Image-2.5 with other important image models using the same benchmark and sample methodology.

View the complete image model comparison

Nano Banana 2 vs. MAI-Image-2.5

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