Skip to main content

Head-to-head comparison

GPT Image 2.5 Sunburst vs. HunyuanImage 3.0 Instruct

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
7
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 GPT Image 2.5 Sunburst and HunyuanImage 3.0 Instruct
AttributeGPT Image 2.5 SunburstHunyuanImage 3.0 Instruct
ProviderOpenAITencent
ReleasedSeptember 8, 2026January 2026
AccessAPIAPI, local
LifecycleNo separate lifecycle noticeNo separate lifecycle notice
WeightsProprietaryOpen weights
ParametersNot published80 billion, 13 billion active
Maximum output3,840 × 2,160 pixelsNot consistently published
Arena configurationSunburstFal
Text-to-image price$210.7 per 1,000 images$90 per 1,000 images
Editing price$210.7 per 1,000 images$90 per 1,000 images
Technical sourceModel sourceVerified 2026-09-24Model sourceVerified 2026-08-15
GPT Image 2.5 SunburstHunyuanImage 3.0 Instruct
Text to Image ArenaUSD per 1,000 images at 1,024 × 1,024 pixels
GPT Image 2.5 Sunburst$210.7
HunyuanImage 3.0 InstructLower price$90
Image Editing ArenaUSD per 1,000 images at 1,024 × 1,024 pixels
GPT Image 2.5 Sunburst$210.7
HunyuanImage 3.0 InstructLower price$90

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.

GPT Image 2.5 SunburstHunyuanImage 3.0 Instruct
Gradually sample test: Typography and layoutMean of three blind ranks across all 30 first outputs, n = 1 each
GPT Image 2.5 Sunburst21.8 / 100
HunyuanImage 3.0 InstructHigher blind-rank score69 / 100
Gradually sample test: Product photographyMean of three blind ranks across all 30 first outputs, n = 1 each
GPT Image 2.5 SunburstHigher blind-rank score97.7 / 100
HunyuanImage 3.0 Instruct55.2 / 100
Gradually sample test: Character and detailMean of three blind ranks across all 30 first outputs, n = 1 each
GPT Image 2.5 Sunburst25.3 / 100
HunyuanImage 3.0 InstructHigher blind-rank score69 / 100
Gradually sample test: InfographicMean of three blind ranks across all 30 first outputs, n = 1 each
GPT Image 2.5 SunburstHigher blind-rank score98.9 / 100
HunyuanImage 3.0 Instruct29.9 / 100

Key to the marks:better valuebetter, but not conclusivetie

Capability benchmark scores for GPT Image 2.5 Sunburst and HunyuanImage 3.0 Instruct
BenchmarkGPT Image 2.5 SunburstHunyuanImage 3.0 Instruct
Gradually sample test: Typography and layout
21.8 / 100
Mean rank: 23.67 (22 / 25 / 24)
Five rubric scores
Headline: 1.67 / 2
Subline: 1.67 / 2
Text control: 1.67 / 2
Visual brief: 1.33 / 2
Layout: 1 / 2
Higher blind-rank score69 / 100
Mean rank: 10 (8 / 10 / 12)
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 score97.7 / 100
Mean rank: 1.67 (2 / 1 / 2)
Five rubric scores
Subject: 1.67 / 2
Time: 1.67 / 2
Watch details: 1.67 / 2
Photography: 1.67 / 2
Exclusions: 1.67 / 2
55.2 / 100
Mean rank: 14 (7 / 18 / 17)
Five rubric scores
Subject: 1.67 / 2
Time: 1.67 / 2
Watch details: 1.33 / 2
Photography: 1.67 / 2
Exclusions: 1.67 / 2
Gradually sample test: Character and detail
25.3 / 100
Mean rank: 22.67 (26 / 26 / 16)
Five rubric scores
Scene: 1 / 2
Wardrobe: 1 / 2
Anatomy: 1 / 2
Props: 1 / 2
Environment: 1 / 2
Higher blind-rank score69 / 100
Mean rank: 10 (20 / 4 / 6)
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 score98.9 / 100
Mean rank: 1.33 (1 / 2 / 1)
Five rubric scores
Title: 1.67 / 2
Sequence: 1.67 / 2
Labels: 1.67 / 2
Diagram: 1.67 / 2
Clarity: 1.67 / 2
29.9 / 100
Mean rank: 21.33 (17 / 23 / 24)
Five rubric scores
Title: 1 / 2
Sequence: 1.67 / 2
Labels: 1.67 / 2
Diagram: 0.67 / 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.

3 shared result series
GPT Image 2.5 SunburstHunyuanImage 3.0 Instruct
Text to Image ArenaBlind preference from the same prompt, higher is better
GPT Image 2.5 SunburstHigher score1,197 Elo
HunyuanImage 3.0 Instruct964 Elo
Image Editing ArenaBlind preference from the same prompt, higher is better
GPT Image 2.5 SunburstHigher score1,180 Elo
HunyuanImage 3.0 Instruct1,027 Elo
LMArena Image Editing: OverallBlind preference from the same prompt, higher is better
GPT Image 2.5 SunburstHigher score1,520.443
HunyuanImage 3.0 Instruct1,302.412

Key to the marks:better valuebetter, but not conclusivetie

Arena benchmark scores for GPT Image 2.5 Sunburst and HunyuanImage 3.0 Instruct
BenchmarkGPT Image 2.5 SunburstHunyuanImage 3.0 InstructSource
Text to Image Arena
Higher score1,197 Elo
Rank 1, 95% confidence interval: ±9, 13,401 ratings
964 Elo
Rank 65, 95% confidence interval: ±9, 5,207 ratings
Artificial AnalysisRetrieved 2026-09-22
Image Editing Arena
Higher score1,180 Elo
Rank 1, 95% confidence interval: ±8, 16,958 ratings
1,027 Elo
Rank 29, 95% confidence interval: ±9, 4,273 ratings
Artificial AnalysisRetrieved 2026-09-22
LMArena Image Editing: Overall
Higher score1,520.443
Rank 1, 95% confidence interval: ±9.21, 6,704 ratings
1,302.412
Rank 22, 95% confidence interval: ±3.39, 307,730 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

HunyuanImage 3.0 Instruct, Character and detail
GPT Image 2.5 Sunburst, Character and detail
GPT Image 2.5 Sunburst
HunyuanImage 3.0 Instruct
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 2.5 Sunburst. Provider OpenAI, 1024x1024, quality high, n=1, model ID gpt-image-2.5-sunburst, generated Sep 28, 2026, 8:51 PM. Source
HunyuanImage 3.0 Instruct. Provider fal.ai, requested 1024x1024, n=1, seed=480451513, prompt expansion disabled, estimated cost $0.094372, model ID fal-ai/hunyuan-image/v3/instruct/text-to-image, generated Aug 14, 2026, 1:51 PM. Source

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

Prompt SHA 256: 985a75b38642a9f0e5e0c0e0c67f1b7f67780d42bd2168fa24e9a7a7a94b0da6

GPT Image 2.5 Sunburst, image SHA 256: 2bcd5e2358dbf9e2f11336ebf6c4a4a15e0a9a10261dd74378d40985ac68ec6d

GPT Image 2.5 Sunburst, request SHA 256: fe156d4933f8a7af7d109e003d79ef3da6654c470fa167c69553d3265dd84ded

HunyuanImage 3.0 Instruct, image SHA 256: 7c813735994e5781c420b23e15898e1d4c8b9a83b24dae9c72e9d7b08fe7ceb4

HunyuanImage 3.0 Instruct, request SHA 256: 7db014c7ede1aa8032b454dd7d23feb8f0b110808d7a8995275bd91a1e6f926c

Infographic

Numbers, labels, and visual organization

HunyuanImage 3.0 Instruct, Infographic
GPT Image 2.5 Sunburst, Infographic
GPT Image 2.5 Sunburst
HunyuanImage 3.0 Instruct
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 2.5 Sunburst. Provider OpenAI, 1024x1024, quality high, n=1, model ID gpt-image-2.5-sunburst, generated Sep 28, 2026, 8:52 PM. Source
HunyuanImage 3.0 Instruct. Provider fal.ai, requested 1024x1024, n=1, seed=1316714523, prompt expansion disabled, estimated cost $0.094372, model ID fal-ai/hunyuan-image/v3/instruct/text-to-image, generated Aug 14, 2026, 1:52 PM. Source

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

Prompt SHA 256: ed65cb4e6a51e2336f8b149ad4cbb16e020f07d527ad94362e719d2dcf91d94f

GPT Image 2.5 Sunburst, image SHA 256: 7dab94e5588be73aefe08f23f9d56ced4e2ddb2b29f754db41b057025cf34847

GPT Image 2.5 Sunburst, request SHA 256: b67e094e50474dd45f816d34ef9e0935a70b24829bc4fc60a4a24d563eba2977

HunyuanImage 3.0 Instruct, image SHA 256: a9c50516fcbe8008d3d67c0651882f7c712aff66ee244b7f8aa7b83c0a67aaab

HunyuanImage 3.0 Instruct, request SHA 256: 7b664cdf0c6f4165d17100e80067cb9d1c950d20b262cf78d2e5c0703da84c5c

Product photography

Materials, reflections, and fine details

HunyuanImage 3.0 Instruct, Product photography
GPT Image 2.5 Sunburst, Product photography
GPT Image 2.5 Sunburst
HunyuanImage 3.0 Instruct
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 2.5 Sunburst. Provider OpenAI, 1024x1024, quality high, n=1, model ID gpt-image-2.5-sunburst, generated Sep 28, 2026, 8:51 PM. Source
HunyuanImage 3.0 Instruct. Provider fal.ai, requested 1024x1024, n=1, seed=1892985637, prompt expansion disabled, estimated cost $0.094372, model ID fal-ai/hunyuan-image/v3/instruct/text-to-image, generated Aug 14, 2026, 1:51 PM. Source

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

Prompt SHA 256: c67fd71e91304458a2feef5c91efa8677260fab0c0099a29a2c52cb579f5b2f3

GPT Image 2.5 Sunburst, image SHA 256: c648276704e06f7925f2325e8ffff0d9d0a9bd6c5bb4866785abac92ce97ff9a

GPT Image 2.5 Sunburst, request SHA 256: fa7b392f661da048749d5294aedea9e6c918a83cbe482cdc70a7f8df267bafec

HunyuanImage 3.0 Instruct, image SHA 256: 89ed8da585fcce3df9f76584dfc426a5142fe3b950c79a306a7ce3b79746ed99

HunyuanImage 3.0 Instruct, request SHA 256: 23b9a3151ee407a3387ae153fd37ebf415ce89861e8ad212ca150c4f1fcd386e

Typography and layout

Legible text, hierarchy, and composition

HunyuanImage 3.0 Instruct, Typography and layout
GPT Image 2.5 Sunburst, Typography and layout
GPT Image 2.5 Sunburst
HunyuanImage 3.0 Instruct
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 2.5 Sunburst. Provider OpenAI, 1024x1024, quality high, n=1, model ID gpt-image-2.5-sunburst, generated Sep 28, 2026, 8:50 PM. Source
HunyuanImage 3.0 Instruct. Provider fal.ai, requested 1024x1024, n=1, seed=1326433162, prompt expansion disabled, estimated cost $0.094372, model ID fal-ai/hunyuan-image/v3/instruct/text-to-image, generated Aug 14, 2026, 2:41 PM. Source

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

Prompt SHA 256: 2e012c3d14ee5dd02203a94f394ca80a5038cdebd6032b25a8b8a221f2255419

GPT Image 2.5 Sunburst, image SHA 256: fd6a3767ba8253869cb94d5346f025541dac924c2190df2c37b366b182986cf8

GPT Image 2.5 Sunburst, request SHA 256: 6fb8eeab411c5e7b600849741e4fa8408361e00074dc89e91e67e9d9e898ef81

HunyuanImage 3.0 Instruct, image SHA 256: 4563cdd9bb047b4df3316484fcc4fe369ba6635f0360e434f45577d013468b6c

HunyuanImage 3.0 Instruct, request SHA 256: efd3bc5cb7cf1e1511bde27609704b11aa672e608c34b4ecd16fb998f45385f3

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 GPT Image 2.5 Sunburst and HunyuanImage 3.0 Instruct 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