Head-to-head comparison

MAI-Image-2.5 vs. FLUX.2 Flex

Compare arena scores with documented retrieval dates, task-specific image pricing, and verified specifications. Text-to-image generation and image editing are never blended into an artificial overall score.

shared result series

shared sample prompts

2026-08-16

latest arena retrieval

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 FLUX.2 Flex
Attribute	MAI-Image-2.5	FLUX.2 Flex
Provider	Microsoft AI	Black Forest Labs
Released	June 2026	November 2025
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	4 Megapixel
Arena configuration	No separate configuration named	Flex
Text-to-image price	$48.1 per 1,000 images	$60 per 1,000 images
Editing price	$48.1 per 1,000 images	$120 per 1,000 images
Technical source	Model sourceVerified 2026-08-15	Model sourceVerified 2026-08-15

MAI-Image-2.5FLUX.2 Flex

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

MAI-Image-2.5$48.1Lower price

FLUX.2 Flex$60

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

MAI-Image-2.5$48.1Lower price

FLUX.2 Flex$120

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

MAI-Image-2.5FLUX.2 Flex

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

MAI-Image-2.51,310 EloHigher arena score

FLUX.2 Flex1,220 Elo

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

MAI-Image-2.51,257 EloHigher arena score

FLUX.2 Flex1,164 Elo

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

MAI-Image-2.51,246.107 arena pointsHigher arena score

FLUX.2 Flex1,171.967 arena points

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

MAI-Image-2.51,277.636 arena pointsHigher arena score

FLUX.2 Flex1,155.954 arena points

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

MAI-Image-2.51,270.066 arena pointsHigher arena score

FLUX.2 Flex1,162.335 arena points

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

MAI-Image-2.51,260.487 arena pointsHigher arena score

FLUX.2 Flex1,173.137 arena points

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

MAI-Image-2.51,256.13 arena pointsHigher arena score

FLUX.2 Flex1,156.466 arena points

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

MAI-Image-2.51,253.013 arena pointsHigher arena score

FLUX.2 Flex1,146.683 arena points

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

MAI-Image-2.51,259.199 arena pointsHigher arena score

FLUX.2 Flex1,144.533 arena points

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

MAI-Image-2.51,282.791 arena pointsHigher arena score

FLUX.2 Flex1,172.004 arena points

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

MAI-Image-2.51,401.879 arena pointsHigher arena score

FLUX.2 Flex1,225.241 arena points

Arena benchmark scores for MAI-Image-2.5 and FLUX.2 Flex
Benchmark	MAI-Image-2.5	FLUX.2 Flex	Source
Text to Image Arena	1,310 EloHigher arena score Rank 5, 95% confidence interval: ±9, 14,529 ratings	1,220 Elo Rank 18, 95% confidence interval: ±11, 4,481 ratings	Artificial AnalysisRetrieved 2026-08-15
Image Editing Arena	1,257 EloHigher arena score Rank 3, 95% confidence interval: ±8, 11,229 ratings	1,164 Elo Rank 33, 95% confidence interval: ±7, 7,827 ratings	Artificial AnalysisRetrieved 2026-08-15
Arena Text to Image: 3D modeling	1,246.107 arena pointsHigher arena score Rank 5, 95% confidence interval: ±9.6, 4,252 ratings	1,171.967 arena points Rank 19, 95% confidence interval: ±7.03, 15,066 ratings	ArenaRetrieved 2026-08-16
Arena Text to Image: Art	1,277.636 arena pointsHigher arena score Rank 3, 95% confidence interval: ±8.37, 6,571 ratings	1,155.954 arena points Rank 28, 95% confidence interval: ±6.38, 21,779 ratings	ArenaRetrieved 2026-08-16
Arena Text to Image: Cartoon	1,270.066 arena pointsHigher arena score Rank 7, 95% confidence interval: ±6.37, 17,440 ratings	1,162.335 arena points Rank 26, 95% confidence interval: ±5.15, 55,850 ratings	ArenaRetrieved 2026-08-16
Arena Text to Image: Commercial design	1,260.487 arena pointsHigher arena score Rank 6, 95% confidence interval: ±6.3, 17,261 ratings	1,173.137 arena points Rank 21, 95% confidence interval: ±4.95, 55,246 ratings	ArenaRetrieved 2026-08-16
Arena Text to Image: Overall	1,256.13 arena pointsHigher arena score Rank 8, 95% confidence interval: ±4.57, 44,940 ratings	1,156.466 arena points Rank 25, 95% confidence interval: ±3.42, 149,402 ratings	ArenaRetrieved 2026-08-16
Arena Text to Image: Photorealism	1,253.013 arena pointsHigher arena score Rank 10, 95% confidence interval: ±6.3, 17,468 ratings	1,146.683 arena points Rank 33, 95% confidence interval: ±4.87, 63,801 ratings	ArenaRetrieved 2026-08-16
Arena Text to Image: Portraits	1,259.199 arena pointsHigher arena score Rank 10, 95% confidence interval: ±7.61, 8,541 ratings	1,144.533 arena points Rank 34, 95% confidence interval: ±5.82, 33,696 ratings	ArenaRetrieved 2026-08-16
Arena Text to Image: Text rendering	1,282.791 arena pointsHigher arena score Rank 7, 95% confidence interval: ±6.6, 15,799 ratings	1,172.004 arena points Rank 22, 95% confidence interval: ±5.14, 49,969 ratings	ArenaRetrieved 2026-08-16
Arena Image Editing: Overall	1,401.879 arena pointsHigher arena score Rank 3, 95% confidence interval: ±3.85, 155,115 ratings	1,225.241 arena points Rank 34, 95% confidence interval: ±3.17, 415,923 ratings	ArenaRetrieved 2026-08-16

Visual comparison

Sample images from documented runs

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

FLUX.2 Flex, Character and detail — FLUX.2 Flex

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
FLUX.2 Flex. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID black-forest-labs/FLUX.2-flex, generated Aug 14, 2026, 12:25 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

FLUX.2 Flex, image SHA 256: 43b43d5782192d7284de2b824dd1caaaa6b25032d22fc3f8565d438b137089f3

FLUX.2 Flex, request SHA 256: fe5b22589e6505017dc44f4729b1bb60b15820ba3673354d03a69c8b82831953

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
FLUX.2 Flex. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID black-forest-labs/FLUX.2-flex, generated Aug 14, 2026, 12:25 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

FLUX.2 Flex, image SHA 256: 105f60cdeb71a27021ffff1ad3c0ad919df4e5c74ad83b4628fbd64a8d795a09

FLUX.2 Flex, request SHA 256: 11d4ec056332340dc822c82021ef10c6a6aa92de6e44dc931a90b7cbb6f14146

Product photography

Materials, reflections, and fine details

FLUX.2 Flex, Product photography — FLUX.2 Flex

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
FLUX.2 Flex. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID black-forest-labs/FLUX.2-flex, generated Aug 14, 2026, 12:25 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

FLUX.2 Flex, image SHA 256: 9fef39b1500635ddbf78bcb8d3d9a68463ce952aa1fab89d12f6efe023907de7

FLUX.2 Flex, request SHA 256: 1c864c5e5d7f1e7008f15466fd0786f801ae94b17939b4f10de9a61c27766a59

Typography and layout

Legible text, hierarchy, and composition

FLUX.2 Flex, Typography and layout — FLUX.2 Flex

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
FLUX.2 Flex. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID black-forest-labs/FLUX.2-flex, generated Aug 14, 2026, 2:01 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

FLUX.2 Flex, image SHA 256: 324f87bf898593446a400abb43bd00eee015fa0a1dc160db0f864402fc0b38af

FLUX.2 Flex, request SHA 256: a0aa716f2a302bdfa59820d2e2c27cc56f730e8e2e4d5b64223d29a6979e1475

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 FLUX.2 Flex with other important image models using the same benchmark and sample methodology.

View the complete image model comparison

MAI-Image-2.5 vs. FLUX.2 Flex

Change image model selection

General specifications and task-specific pricing

Shared arena benchmarks

Sample images from documented runs

Character and detail

Infographic

Product photography

Typography and layout

An Elo score is not a verdict on creativity

Related image model comparisons