Skip to main content

Black Forest LabsImage model matchup

FLUX.2 Maxvs.FLUX.2 Flex

Is the extra cost worth it?

Probably not. In our own benchmark GraduallyBench Image v2, both are on par. In the arena both are on par. FLUX.2 Max costs 1.2 times as much per image.

GraduallyBench Image v2Our own benchmark0 to 100 · higher is better
67

FLUX.2 Max

Rank 37 of 108

66

FLUX.2 Flex

Rank 40 of 108

Arena ratingfrom votes by users · higher is better
1,161

FLUX.2 Max

Rank 15 of 21

1,156

FLUX.2 Flex

Rank 16 of 21

Price per imagedollars through the API · lower is better
$0.07

FLUX.2 Max

$0.06

FLUX.2 Flex

Ranks among the 21 image models with an arena rating and the 108 with a GraduallyBench Image v2 run; prices compared with 28 models with an API price.

Test images from GraduallyBench Image v2

Our own benchmarkThe images come from GraduallyBench Image v2, our own benchmark: every model gets the same four tasks, and two AI judges compare the images in pairs and blind.

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

FLUX.2 Max: Product photography, first image from the fixed test run
FLUX.2 Max81 out of 100
FLUX.2 Flex: Product photography, first image from the fixed test run
FLUX.2 Flex71 out of 100

Result for “Product photography”:FLUX.2 Max slightly ahead

Prompt given to both modelsCreate 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.

What the rating looks at: Materials, reflections, and fine details.

“Ahead”: the 95 % ranges of both values do not overlap. “Slightly ahead”: a higher value, but the ranges overlap.

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

FLUX.2 Max: together, 1024x1024, n=1, seed=provider random, steps=50, generated Aug 14, 2026, 12:23 PM. Source

FLUX.2 Flex: together, 1024x1024, n=1, seed=provider random, provider default steps, generated Aug 14, 2026, 12:25 PM. Source

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

FLUX.2 Max image SHA 256: a0a2cef301582c47a8dca69ccd1c52212c37ca6c058d7185a880a7856713cd9e

FLUX.2 Flex image SHA 256: 43b43d5782192d7284de2b824dd1caaaa6b25032d22fc3f8565d438b137089f3

Infographic

FLUX.2 Max: together, 1024x1024, n=1, seed=provider random, steps=50, generated Aug 14, 2026, 12:24 PM. Source

FLUX.2 Flex: together, 1024x1024, n=1, seed=provider random, provider default steps, generated Aug 14, 2026, 12:25 PM. Source

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

FLUX.2 Max image SHA 256: 9321457355d5a9630073632fb6441bf388da1c4ee8e5d58e58cd0603ce756a09

FLUX.2 Flex image SHA 256: 105f60cdeb71a27021ffff1ad3c0ad919df4e5c74ad83b4628fbd64a8d795a09

Product photography

FLUX.2 Max: together, 1024x1024, n=1, seed=provider random, steps=50, generated Aug 14, 2026, 12:23 PM. Source

FLUX.2 Flex: together, 1024x1024, n=1, seed=provider random, provider default steps, generated Aug 14, 2026, 12:25 PM. Source

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

FLUX.2 Max image SHA 256: dd6ad8d1ec45154727d9ddf573ef10da5225899820055318d23bcd4e5a1e930c

FLUX.2 Flex image SHA 256: 9fef39b1500635ddbf78bcb8d3d9a68463ce952aa1fab89d12f6efe023907de7

Typography and layout

FLUX.2 Max: together, 1024x1024, n=1, seed=provider random, steps=50, generated Aug 14, 2026, 2:00 PM. Source

FLUX.2 Flex: together, 1024x1024, n=1, seed=provider random, provider default steps, generated Aug 14, 2026, 2:01 PM. Source

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

FLUX.2 Max image SHA 256: 3eb2daf01c749ee25d86c2e4f55d6d3d81cfb4590eb0343f9a4bb3d0a70d19bc

FLUX.2 Flex image SHA 256: 324f87bf898593446a400abb43bd00eee015fa0a1dc160db0f864402fc0b38af

Subscription and API

FLUX.2 Max

Subscription
No Black Forest Labs subscription includes this model. Through other providers from $4.99 a month (Poe Basic, with limited points). 28 plans in Germany.
Via API
$0.07 per image, 100 images $7.
Weights
Closed weights.

FLUX.2 Flex

Subscription
No Black Forest Labs subscription includes this model. Through other providers from $4.99 a month (Poe Basic, with limited points). 26 plans in Germany.
Via API
$0.06 per image, 100 images $6.
Weights
Closed weights.

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

Arena rating (LMArena) from Nov 13, 2026 · GraduallyBench Image v2 from Nov 7, 2026 · API prices from Nov 12, 2026 · Subscription database from Sep 29, 2026 (49 days old)

All data side by side

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

KennzahlFLUX.2 MaxFLUX.2 Flex
Ratings
Arena ratingfrom votes by users, higher is better1,1611,156
Arena rankRank 15 of 21Rank 16 of 21
Arena votesmore votes, a safer rating120,408152,898
GraduallyBench Image v2our own benchmark, 0 to 1006766
GraduallyBench Image v2 by task
Typography and layoutLegible text, hierarchy, and composition7681
Product photographyMaterials, reflections, and fine details8171
Character and detailAnatomy, clothing, and spatial consistency6165
InfographicNumbers, labels, and visual organization4946
API price
Per imagelower is better$0.07$0.06
100 images$7$6
Profile
ReleasedDecember 2025November 2025
Weightsopen means: runs locallyproprietaryproprietary
AccessAPI, Web appAPI, Web app
Parametersnot publishednot published
Largest output4 Megapixel4 Megapixel
Plans in Germanynaming exactly this model2826

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

Sources: FLUX.2 Max model source (verified Sep 24, 2026) · FLUX.2 Flex model source (verified Sep 24, 2026)

Arena ratings by category

From blind votes on Artificial Analysis and LMArena; the sources are named under the card. “Ahead” means the lead is clear.

Rating per categoryfrom votes by users · higher is betterFLUX.2 MaxFLUX.2 Flex
Text to Image ArenaFLUX.2 Max: 1,022FLUX.2 Flex: 1,028level
Image Editing ArenaFLUX.2 Max: 998FLUX.2 Flex: 995level
Text to Image: 3D modelingFLUX.2 Max: 1,161FLUX.2 Flex: 1,173level
Text to Image: ArtFLUX.2 Max: 1,168FLUX.2 Flex: 1,156level
Text to Image: CartoonFLUX.2 Max: 1,167FLUX.2 Flex: 1,164level
Text to Image: Commercial designFLUX.2 Max: 1,163FLUX.2 Flex: 1,172level
Text to Image: OverallFLUX.2 Max: 1,161FLUX.2 Flex: 1,156level
Text to Image: PhotorealismFLUX.2 Max: 1,161FLUX.2 Flex: 1,145FLUX.2 Max ahead
Text to Image: PortraitsFLUX.2 Max: 1,156FLUX.2 Flex: 1,144FLUX.2 Max ahead
Text to Image: Text renderingFLUX.2 Max: 1,165FLUX.2 Flex: 1,171level
Image Editing: Multi-image editingFLUX.2 Max: 1,250FLUX.2 Flex: 1,235FLUX.2 Max ahead
Image Editing: OverallFLUX.2 Max: 1,262FLUX.2 Flex: 1,224FLUX.2 Max ahead

Artificial Analysis from Nov 12, 2026 · LMArena from Nov 13, 2026

All individual values with sources
RatingFLUX.2 MaxFLUX.2 FlexSource
Text to Image Arena1,0221,028Artificial AnalysisRetrieved Nov 12, 2026
Image Editing Arena998995Artificial AnalysisRetrieved Nov 12, 2026
Text to Image: 3D modeling1,1611,173LMArenaRetrieved Nov 13, 2026
Text to Image: Art1,1681,156LMArenaRetrieved Nov 13, 2026
Text to Image: Cartoon1,1671,164LMArenaRetrieved Nov 13, 2026
Text to Image: Commercial design1,1631,172LMArenaRetrieved Nov 13, 2026
Text to Image: Overall1,1611,156LMArenaRetrieved Nov 13, 2026
Text to Image: Photorealism1,1611,145LMArenaRetrieved Nov 13, 2026
Text to Image: Portraits1,1561,144LMArenaRetrieved Nov 13, 2026
Text to Image: Text rendering1,1651,171LMArenaRetrieved Nov 13, 2026
Image Editing: Multi-image editing1,2501,235LMArenaRetrieved Nov 13, 2026
Image Editing: Overall1,2621,224LMArenaRetrieved Nov 13, 2026

More comparisons

Compare FLUX.2 Max and FLUX.2 Flex with the models people compare them with most often.

Compare another matchup