Head-to-head comparison

GPT Image 1.5 vs. FLUX.2 Klein 9B

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: 23
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 GPT Image 1.5 and FLUX.2 Klein 9B
Attribute	GPT Image 1.5	FLUX.2 Klein 9B
Provider	OpenAI	Black Forest Labs
Released	December 2025	January 2026
Access	API, Web app	API, local
Lifecycle	Marked as deprecated by OpenAI; removed from the API on December 1, 2026 Status source	Weights released under the FLUX Non-Commercial License Status source
Weights	Proprietary	Open weights
Parameters	Not published	9 billion
Maximum output	1,536 × 1,024 pixels	4 Megapixel
Arena configuration	High	9B
Text-to-image price	$133 per 1,000 images	$15 per 1,000 images
Editing price	$133 per 1,000 images	$17 per 1,000 images
Technical source	Model sourceVerified 2026-08-15	Model sourceVerified 2026-09-24

GPT Image 1.5FLUX.2 Klein 9B

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

GPT Image 1.5$133

FLUX.2 Klein 9B$15

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

GPT Image 1.5$133

FLUX.2 Klein 9B$17

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. This pair also shares 7 results from published research benchmarks.

GPT Image 1.5FLUX.2 Klein 9B

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

GPT Image 1.529.9 / 100

FLUX.2 Klein 9B10.3 / 100

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

GPT Image 1.543.7 / 100

FLUX.2 Klein 9B43.7 / 100

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

GPT Image 1.577 / 100

FLUX.2 Klein 9B28.7 / 100

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

GPT Image 1.542.5 / 100

FLUX.2 Klein 9B14.9 / 100

Key to the marks:better valuebetter, but not conclusivetie

Capability benchmark scores for GPT Image 1.5 and FLUX.2 Klein 9B
Benchmark	GPT Image 1.5	FLUX.2 Klein 9B
WISE Verified overall	Higher benchmark score82.5 %	44 %
WISE culture	Higher benchmark score89 %	49 %
WISE time	Higher benchmark score69.17 %	39.17 %
WISE space	Higher benchmark score88.33 %	55 %
WISE biology	Higher benchmark score80 %	38.33 %
WISE physics	Higher benchmark score75.83 %	48.33 %
WISE chemistry	Higher benchmark score77.5 %	22.5 %
Gradually sample test: Typography and layout	Higher blind-rank score29.9 / 100 Mean rank: 21.33 (23 / 22 / 19) Five rubric scores Headline: 1.67 / 2 Subline: 1.67 / 2 Text control: 1.67 / 2 Visual brief: 1.33 / 2 Layout: 1 / 2	10.3 / 100 Mean rank: 27 (27 / 27 / 27) Five rubric scores Headline: 1.67 / 2 Subline: 0.67 / 2 Text control: 1 / 2 Visual brief: 1.67 / 2 Layout: 1 / 2
Gradually sample test: Product photography	Tie43.7 / 100 Mean rank: 17.33 (22 / 8 / 22) Five rubric scores Subject: 1.67 / 2 Time: 1 / 2 Watch details: 1.67 / 2 Photography: 1.67 / 2 Exclusions: 1.67 / 2	Tie43.7 / 100 Mean rank: 17.33 (13 / 19 / 20) Five rubric scores Subject: 1.67 / 2 Time: 1.33 / 2 Watch details: 1.67 / 2 Photography: 1.67 / 2 Exclusions: 1.67 / 2
Gradually sample test: Character and detail	Higher blind-rank score77 / 100 Mean rank: 7.67 (6 / 5 / 12) Five rubric scores Scene: 1 / 2 Wardrobe: 1 / 2 Anatomy: 1 / 2 Props: 1 / 2 Environment: 1 / 2	28.7 / 100 Mean rank: 21.67 (22 / 17 / 26) 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 score42.5 / 100 Mean rank: 17.67 (20 / 14 / 19) Five rubric scores Title: 1.67 / 2 Sequence: 1.67 / 2 Labels: 1 / 2 Diagram: 1.67 / 2 Clarity: 1 / 2	14.9 / 100 Mean rank: 25.67 (25 / 26 / 26) Five rubric scores Title: 1.67 / 2 Sequence: 1 / 2 Labels: 0.33 / 2 Diagram: 0.67 / 2 Clarity: 0.33 / 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

GPT Image 1.5FLUX.2 Klein 9B

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

GPT Image 1.51,102 Elo

FLUX.2 Klein 9B940 Elo

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

GPT Image 1.51,103 Elo

FLUX.2 Klein 9B1,014 Elo

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

GPT Image 1.51,214.044

FLUX.2 Klein 9B1,078.703

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

GPT Image 1.51,224.786

FLUX.2 Klein 9B1,078.937

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

GPT Image 1.51,245.019

FLUX.2 Klein 9B1,064.062

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

GPT Image 1.51,240.235

FLUX.2 Klein 9B1,069.617

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

GPT Image 1.51,239.16

FLUX.2 Klein 9B1,069.544

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

GPT Image 1.51,249.33

FLUX.2 Klein 9B1,090.199

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

GPT Image 1.51,261.708

FLUX.2 Klein 9B1,091.959

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

GPT Image 1.51,253.437

FLUX.2 Klein 9B1,057.327

LMArena Image Editing: Multi-image editingBlind preference from the same prompt, higher is better

GPT Image 1.51,342.523

FLUX.2 Klein 9B1,212.815

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

GPT Image 1.51,370.19

FLUX.2 Klein 9B1,224.422

Key to the marks:better valuebetter, but not conclusivetie

Arena benchmark scores for GPT Image 1.5 and FLUX.2 Klein 9B
Benchmark	GPT Image 1.5	FLUX.2 Klein 9B	Source
Text to Image Arena	Higher score1,102 Elo Rank 9, 95% confidence interval: ±9, 14,748 ratings	940 Elo Rank 75, 95% confidence interval: ±8, 10,360 ratings	Artificial AnalysisRetrieved 2026-09-22
Image Editing Arena	Higher score1,103 Elo Rank 12, 95% confidence interval: ±9, 12,789 ratings	1,014 Elo Rank 32, 95% confidence interval: ±9, 5,177 ratings	Artificial AnalysisRetrieved 2026-09-22
LMArena Text to Image: 3D modeling	Higher score1,214.044 Rank 15, 95% confidence interval: ±6.6, 15,526 ratings	1,078.703 Rank 58, 95% confidence interval: ±6.95, 13,817 ratings	LMArenaRetrieved 2026-09-19
LMArena Text to Image: Art	Higher score1,224.786 Rank 14, 95% confidence interval: ±5.9, 21,424 ratings	1,078.937 Rank 56, 95% confidence interval: ±6.28, 19,040 ratings	LMArenaRetrieved 2026-09-19
LMArena Text to Image: Cartoon	Higher score1,245.019 Rank 14, 95% confidence interval: ±4.72, 59,294 ratings	1,064.062 Rank 58, 95% confidence interval: ±5.02, 52,993 ratings	LMArenaRetrieved 2026-09-19
LMArena Text to Image: Commercial design	Higher score1,240.235 Rank 14, 95% confidence interval: ±4.6, 58,887 ratings	1,069.617 Rank 59, 95% confidence interval: ±4.6, 55,147 ratings	LMArenaRetrieved 2026-09-19
LMArena Text to Image: Overall	Higher score1,239.16 Rank 15, 95% confidence interval: ±3.24, 151,702 ratings	1,069.544 Rank 58, 95% confidence interval: ±3.26, 142,642 ratings	LMArenaRetrieved 2026-09-19
LMArena Text to Image: Photorealism	Higher score1,249.33 Rank 15, 95% confidence interval: ±4.7, 60,842 ratings	1,090.199 Rank 57, 95% confidence interval: ±4.71, 60,271 ratings	LMArenaRetrieved 2026-09-19
LMArena Text to Image: Portraits	Higher score1,261.708 Rank 12, 95% confidence interval: ±5.81, 29,731 ratings	1,091.959 Rank 58, 95% confidence interval: ±5.75, 32,705 ratings	LMArenaRetrieved 2026-09-19
LMArena Text to Image: Text rendering	Higher score1,253.437 Rank 16, 95% confidence interval: ±4.84, 54,527 ratings	1,057.327 Rank 59, 95% confidence interval: ±4.78, 51,597 ratings	LMArenaRetrieved 2026-09-19
LMArena Image Editing: Multi-image editing	Higher score1,342.523 Rank 11, 95% confidence interval: ±3.62, 192,446 ratings	1,212.815 Rank 27, 95% confidence interval: ±3.99, 148,069 ratings	LMArenaRetrieved 2026-09-19
LMArena Image Editing: Overall	Higher score1,370.19 Rank 15, 95% confidence interval: ±2.81, 566,510 ratings	1,224.422 Rank 39, 95% confidence interval: ±2.91, 507,078 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.

GPT Image 1.5. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID openai/gpt-image-1.5, generated Aug 14, 2026, 12:17 PM. Source
FLUX.2 Klein 9B. Provider fal.ai, requested 1024x1024, n=1, seed=1587849924, estimated cost $0.006291, model ID fal-ai/flux-2/klein/9b, generated Aug 14, 2026, 1:52 PM. Source

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

Prompt SHA 256: 985a75b38642a9f0e5e0c0e0c67f1b7f67780d42bd2168fa24e9a7a7a94b0da6

GPT Image 1.5, image SHA 256: 0dff52ccd39400ac66ac8870c9ea937512ff1474688e70118688f420c38c2296

GPT Image 1.5, request SHA 256: 5199631ac6ff07633dd2fb6ab61c918c26e1e02f37e6131828072233ac04527d

FLUX.2 Klein 9B, image SHA 256: 84eceab680e59de6b9d4e68b3c21f6515ce093ff7d110992049e847570dd565f

FLUX.2 Klein 9B, request SHA 256: 5d005ee24926d68b7d2299b8ecbe4e14919f652761f6de2568a043f2a6258da0

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.

GPT Image 1.5. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID openai/gpt-image-1.5, generated Aug 14, 2026, 12:17 PM. Source
FLUX.2 Klein 9B. Provider fal.ai, requested 1024x1024, n=1, seed=1082231541, estimated cost $0.006291, model ID fal-ai/flux-2/klein/9b, generated Aug 14, 2026, 1:52 PM. Source

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

Prompt SHA 256: ed65cb4e6a51e2336f8b149ad4cbb16e020f07d527ad94362e719d2dcf91d94f

GPT Image 1.5, image SHA 256: 1c9ff59c32621c8b48b002dacb0ae66487262280c7c0a5b3d6456c81b248ebe9

GPT Image 1.5, request SHA 256: 7f1efc9531f1e6bed7d61a11c637add9fd892001aea2bb2781f8d89c79a2eb03

FLUX.2 Klein 9B, image SHA 256: 1d2eb263ca5a25794a88df7bb04f5c13e10ed9a289371d1dcc7ed6d6e0a297e2

FLUX.2 Klein 9B, request SHA 256: 8b8014fc63f520d73ff57d3d8df5eae880097383167d44918b963f2830d09940

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.

GPT Image 1.5. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID openai/gpt-image-1.5, generated Aug 14, 2026, 12:16 PM. Source
FLUX.2 Klein 9B. Provider fal.ai, requested 1024x1024, n=1, seed=1388538280, estimated cost $0.006291, model ID fal-ai/flux-2/klein/9b, generated Aug 14, 2026, 1:39 PM. Source

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

Prompt SHA 256: c67fd71e91304458a2feef5c91efa8677260fab0c0099a29a2c52cb579f5b2f3

GPT Image 1.5, image SHA 256: 67cfa2f324447027ceb5f82e9446d40a1395b46ce425890a74606b4d97731cf6

GPT Image 1.5, request SHA 256: c850843a298631a4076c5d2686de8e9d7223534f2b8ca53505f437862718bef9

FLUX.2 Klein 9B, image SHA 256: e7208f19ccfb9b810b9648cb1861797b7155ad91933d1660059236cef413ebe0

FLUX.2 Klein 9B, request SHA 256: 21e2c14d1b6315c30134e1390f531349608855d4ef1a87527e6d0ba57b2974ca

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.

GPT Image 1.5. Provider Together, 1024x1024, n=1, seed=provider random, provider default steps, model ID openai/gpt-image-1.5, generated Aug 14, 2026, 1:59 PM. Source
FLUX.2 Klein 9B. Provider fal.ai, requested 1024x1024, n=1, seed=1340991019, estimated cost $0.006291, model ID fal-ai/flux-2/klein/9b, generated Aug 14, 2026, 2:41 PM. Source

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

Prompt SHA 256: 2e012c3d14ee5dd02203a94f394ca80a5038cdebd6032b25a8b8a221f2255419

GPT Image 1.5, image SHA 256: 6a4cec86850fd371b65274198e2bf630b3cf36a096f9fb953d4bfe17c3222ebe

GPT Image 1.5, request SHA 256: 9c3a396aecfcaae3f8a25edbe5c8c44d0d33199d7ba29efda864d2b0221c3250

FLUX.2 Klein 9B, image SHA 256: c5f23870e70f2245d24a3689f2579ceb770e5edf8c3c89b7d6ed7ae138f262f6

FLUX.2 Klein 9B, request SHA 256: 530872e813e988ba95025956a3743c6111120af963d90b8970a8bf3eced5547b

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 GPT Image 1.5 and FLUX.2 Klein 9B 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

GPT Image 1.5 vs. FLUX.2 Klein 9B

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