Skip to main content

Head-to-head comparison

FLUX.2 Max vs. FLUX.2 Flex

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
16
shared sample prompts
4
latest arena retrieval
2026-09-22

Change image model selection

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 FLUX.2 Max and FLUX.2 Flex
AttributeFLUX.2 MaxFLUX.2 Flex
ProviderBlack Forest LabsBlack Forest Labs
ReleasedDecember 2025November 2025
AccessAPI, Web appAPI, Web app
LifecycleNo separate lifecycle noticeNo separate lifecycle notice
WeightsProprietaryProprietary
ParametersNot publishedNot published
Maximum output4 Megapixel4 Megapixel
Arena configurationMaxFlex
Text-to-image price$70 per 1,000 images$60 per 1,000 images
Editing price$140 per 1,000 images$120 per 1,000 images
Technical sourceModel sourceVerified 2026-09-24Model sourceVerified 2026-09-24
FLUX.2 MaxFLUX.2 Flex
Text to Image ArenaUSD per 1,000 images at 1,024 × 1,024 pixels
FLUX.2 Max$70
FLUX.2 FlexLower price$60
Image Editing ArenaUSD per 1,000 images at 1,024 × 1,024 pixels
FLUX.2 Max$140
FLUX.2 FlexLower price$120

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.

FLUX.2 MaxFLUX.2 Flex
Gradually sample test: Typography and layoutMean of three blind ranks across all 30 first outputs, n = 1 each
FLUX.2 MaxTie66.7 / 100
FLUX.2 FlexTie66.7 / 100
Gradually sample test: Product photographyMean of three blind ranks across all 30 first outputs, n = 1 each
FLUX.2 MaxHigher blind-rank score56.3 / 100
FLUX.2 Flex52.9 / 100
Gradually sample test: Character and detailMean of three blind ranks across all 30 first outputs, n = 1 each
FLUX.2 MaxHigher blind-rank score71.3 / 100
FLUX.2 Flex54 / 100
Gradually sample test: InfographicMean of three blind ranks across all 30 first outputs, n = 1 each
FLUX.2 MaxHigher blind-rank score28.7 / 100
FLUX.2 Flex24.1 / 100

Key to the marks:better valuebetter, but not conclusivetie

Capability benchmark scores for FLUX.2 Max and FLUX.2 Flex
BenchmarkFLUX.2 MaxFLUX.2 Flex
Gradually sample test: Typography and layout
Tie66.7 / 100
Mean rank: 10.67 (16 / 11 / 5)
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
Tie66.7 / 100
Mean rank: 10.67 (17 / 12 / 3)
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
Higher blind-rank score56.3 / 100
Mean rank: 13.67 (15 / 14 / 12)
Five rubric scores
Subject: 1.67 / 2
Time: 1.67 / 2
Watch details: 1.67 / 2
Photography: 1.67 / 2
Exclusions: 1.67 / 2
52.9 / 100
Mean rank: 14.67 (14 / 16 / 14)
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
Higher blind-rank score71.3 / 100
Mean rank: 9.33 (4 / 15 / 9)
Five rubric scores
Scene: 1 / 2
Wardrobe: 1 / 2
Anatomy: 1 / 2
Props: 1 / 2
Environment: 1 / 2
54 / 100
Mean rank: 14.33 (16 / 20 / 7)
Five rubric scores
Scene: 1 / 2
Wardrobe: 1 / 2
Anatomy: 1 / 2
Props: 1 / 2
Environment: 1 / 2
Gradually sample test: Infographic
Higher blind-rank score28.7 / 100
Mean rank: 21.67 (23 / 17 / 25)
Five rubric scores
Title: 1.67 / 2
Sequence: 1.67 / 2
Labels: 1 / 2
Diagram: 1 / 2
Clarity: 0.67 / 2
24.1 / 100
Mean rank: 23 (22 / 24 / 23)
Five rubric scores
Title: 1.67 / 2
Sequence: 1.33 / 2
Labels: 0.67 / 2
Diagram: 1 / 2
Clarity: 0.67 / 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.

12 shared result series
FLUX.2 MaxFLUX.2 Flex
Text to Image ArenaBlind preference from the same prompt, higher is better
FLUX.2 Max1,022 Elo
FLUX.2 FlexNo clear lead1,026 Elo
Image Editing ArenaBlind preference from the same prompt, higher is better
FLUX.2 Max997 Elo
FLUX.2 FlexNo clear lead1,006 Elo
LMArena Text to Image: 3D modelingBlind preference from the same prompt, higher is better
FLUX.2 Max1,161.397
FLUX.2 FlexNo clear lead1,172.339
LMArena Text to Image: ArtBlind preference from the same prompt, higher is better
FLUX.2 MaxHigher score1,169.986
FLUX.2 Flex1,155.555
LMArena Text to Image: CartoonBlind preference from the same prompt, higher is better
FLUX.2 MaxNo clear lead1,169.356
FLUX.2 Flex1,162.266
LMArena Text to Image: Commercial designBlind preference from the same prompt, higher is better
FLUX.2 Max1,164.737
FLUX.2 FlexNo clear lead1,173.172
LMArena Text to Image: OverallBlind preference from the same prompt, higher is better
FLUX.2 MaxNo clear lead1,162.042
FLUX.2 Flex1,156.503
LMArena Text to Image: PhotorealismBlind preference from the same prompt, higher is better
FLUX.2 MaxHigher score1,160.996
FLUX.2 Flex1,146.875
LMArena Text to Image: PortraitsBlind preference from the same prompt, higher is better
FLUX.2 MaxHigher score1,157.109
FLUX.2 Flex1,144.629
LMArena Text to Image: Text renderingBlind preference from the same prompt, higher is better
FLUX.2 Max1,167.242
FLUX.2 FlexNo clear lead1,171.992
LMArena Image Editing: Multi-image editingBlind preference from the same prompt, higher is better
FLUX.2 MaxHigher score1,250.292
FLUX.2 Flex1,234.148
LMArena Image Editing: OverallBlind preference from the same prompt, higher is better
FLUX.2 MaxHigher score1,261.81
FLUX.2 Flex1,225.241

Key to the marks:better valuebetter, but not conclusivetie

Arena benchmark scores for FLUX.2 Max and FLUX.2 Flex
BenchmarkFLUX.2 MaxFLUX.2 FlexSource
Text to Image Arena
1,022 Elo
Rank 25, 95% confidence interval: ±8, 10,860 ratings
No clear lead1,026 Elo
Rank 21, 95% confidence interval: ±9, 5,931 ratings
Artificial AnalysisRetrieved 2026-09-22
Image Editing Arena
997 Elo
Rank 45, 95% confidence interval: ±9, 5,139 ratings
No clear lead1,006 Elo
Rank 38, 95% confidence interval: ±8, 5,601 ratings
Artificial AnalysisRetrieved 2026-09-22
LMArena Text to Image: 3D modeling
1,161.397
Rank 28, 95% confidence interval: ±7.37, 11,586 ratings
No clear lead1,172.339
Rank 24, 95% confidence interval: ±7.04, 15,061 ratings
LMArenaRetrieved 2026-09-19
LMArena Text to Image: Art
Higher score1,169.986
Rank 26, 95% confidence interval: ±6.55, 16,551 ratings
1,155.555
Rank 31, 95% confidence interval: ±6.39, 21,767 ratings
LMArenaRetrieved 2026-09-19
LMArena Text to Image: Cartoon
No clear lead1,169.356
Rank 26, 95% confidence interval: ±5.37, 42,883 ratings
1,162.266
Rank 29, 95% confidence interval: ±5.16, 55,805 ratings
LMArenaRetrieved 2026-09-19
LMArena Text to Image: Commercial design
1,164.737
Rank 27, 95% confidence interval: ±5.04, 44,226 ratings
No clear lead1,173.172
Rank 24, 95% confidence interval: ±4.96, 55,214 ratings
LMArenaRetrieved 2026-09-19
LMArena Text to Image: Overall
No clear lead1,162.042
Rank 25, 95% confidence interval: ±3.55, 117,339 ratings
1,156.503
Rank 27, 95% confidence interval: ±3.43, 149,288 ratings
LMArenaRetrieved 2026-09-19
LMArena Text to Image: Photorealism
Higher score1,160.996
Rank 27, 95% confidence interval: ±4.96, 50,605 ratings
1,146.875
Rank 36, 95% confidence interval: ±4.88, 63,739 ratings
LMArenaRetrieved 2026-09-19
LMArena Text to Image: Portraits
Higher score1,157.109
Rank 30, 95% confidence interval: ±6.04, 26,736 ratings
1,144.629
Rank 37, 95% confidence interval: ±5.83, 33,656 ratings
LMArenaRetrieved 2026-09-19
LMArena Text to Image: Text rendering
1,167.242
Rank 26, 95% confidence interval: ±5.28, 40,341 ratings
No clear lead1,171.992
Rank 25, 95% confidence interval: ±5.15, 49,929 ratings
LMArenaRetrieved 2026-09-19
LMArena Image Editing: Multi-image editing
Higher score1,250.292
Rank 21, 95% confidence interval: ±4.31, 136,199 ratings
1,234.148
Rank 24, 95% confidence interval: ±4.35, 125,558 ratings
LMArenaRetrieved 2026-09-19
LMArena Image Editing: Overall
Higher score1,261.81
Rank 29, 95% confidence interval: ±3.2, 352,883 ratings
1,225.241
Rank 38, 95% confidence interval: ±3.18, 415,750 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

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

FLUX.2 Max. Provider Together, 1024x1024, n=1, seed=provider random, steps=50, model ID black-forest-labs/FLUX.2-max, generated Aug 14, 2026, 12:23 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

FLUX.2 Max, image SHA 256: a0a2cef301582c47a8dca69ccd1c52212c37ca6c058d7185a880a7856713cd9e

FLUX.2 Max, request SHA 256: 0267e820f1d771485d5a0e44b93a6b996c2fb12f6547a199eb3c22d4cf8e21f3

FLUX.2 Flex, image SHA 256: 43b43d5782192d7284de2b824dd1caaaa6b25032d22fc3f8565d438b137089f3

FLUX.2 Flex, request SHA 256: fe5b22589e6505017dc44f4729b1bb60b15820ba3673354d03a69c8b82831953

Infographic

Numbers, labels, and visual organization

FLUX.2 Flex, Infographic
FLUX.2 Max, Infographic
FLUX.2 Max
FLUX.2 Flex
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.

FLUX.2 Max. Provider Together, 1024x1024, n=1, seed=provider random, steps=50, model ID black-forest-labs/FLUX.2-max, generated Aug 14, 2026, 12:24 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

FLUX.2 Max, image SHA 256: 9321457355d5a9630073632fb6441bf388da1c4ee8e5d58e58cd0603ce756a09

FLUX.2 Max, request SHA 256: 46911d2cf3eb49e0c0439477c802fc24910b2658b19d562a327af2e1b3f3faf1

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 Max, Product photography
FLUX.2 Max
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.

FLUX.2 Max. Provider Together, 1024x1024, n=1, seed=provider random, steps=50, model ID black-forest-labs/FLUX.2-max, generated Aug 14, 2026, 12:23 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

FLUX.2 Max, image SHA 256: dd6ad8d1ec45154727d9ddf573ef10da5225899820055318d23bcd4e5a1e930c

FLUX.2 Max, request SHA 256: 3c90a7839c60af903a8abb6d7b2b4af4df1320aabffcc84361491964161bcf9e

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 Max, Typography and layout
FLUX.2 Max
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.

FLUX.2 Max. Provider Together, 1024x1024, n=1, seed=provider random, steps=50, model ID black-forest-labs/FLUX.2-max, generated Aug 14, 2026, 2:00 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

FLUX.2 Max, image SHA 256: 3eb2daf01c749ee25d86c2e4f55d6d3d81cfb4590eb0343f9a4bb3d0a70d19bc

FLUX.2 Max, request SHA 256: 10a63b4db9e0b1529ab3d891fdb504c5716d30aff6a5cc7bd0312790105eba22

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

Related image model comparisons

Compare FLUX.2 Max and FLUX.2 Flex 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