Skip to main content

Stable Diffusion 3.5 Largevs.HunyuanImage 3.0 Instruct Distil

Which one is better?

We have not tested HunyuanImage 3.0 Instruct Distil ourselves yet. HunyuanImage 3.0 Instruct Distil has no arena rating yet. Neither has an API price.

Same prompt, two images

Same task, the first image of each.

Stable Diffusion 3.5 Large: Typography and layout, first image from the fixed test run
Stable Diffusion 3.5 Large11 out of 100

No image from the four fixed tasks for HunyuanImage 3.0 Instruct Distil yet.This model does not yet have a complete GraduallyBench run.

HunyuanImage 3.0 Instruct Distilnot tested yet

Result for “Typography and layout”:only Stable Diffusion 3.5 Large tested

Prompt given to both modelsCreate 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.

What the rating looks at: Legible text, hierarchy, and composition.

“Ahead”: better in all three rating rounds. “Slightly ahead”: a higher value, but not in every round.

Missing image run for HunyuanImage 3.0 Instruct Distil

This model does not yet have a complete GraduallyBench run. Run the missing fixed tasks, archive the first output of each, and evaluate them blind.

Documentation

The numbers at a glance

Arena ratingfrom votes by users · higher is better
938

Stable Diffusion 3.5 Large

Rank 22 of 22

n/a

HunyuanImage 3.0 Instruct Distil

not in the arena

GraduallyBenchour own rating, 0 to 100 · higher is better
18

Stable Diffusion 3.5 Large

Rank 67 of 74

n/a

HunyuanImage 3.0 Instruct Distil

not tested yet

Price per imagedollars through the API · lower is better
n/a

Stable Diffusion 3.5 Large

no API price

n/a

HunyuanImage 3.0 Instruct Distil

no API price

Ranks among the 22 image models with an arena rating and the 74 with a GraduallyBench run; prices compared with 28 models with an API price.

Stable Diffusion 3.5 Large

Subscription
n/a No plan in Germany names exactly this model.
Via API
No API price known. Access: API, local.
License
Open weights.

HunyuanImage 3.0 Instruct Distil

Subscription
n/a No plan in Germany names exactly this model.
Via API
No API price known. Access: local.
License
Open weights.

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

Arena rating (LMArena) from Oct 28, 2026 · GraduallyBench from Nov 1, 2026 · Subscription database from Sep 29, 2026 (34 days old)

All data side by side

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

KennzahlStable Diffusion 3.5 LargeHunyuanImage 3.0 Instruct Distil
Ratings
Arena ratingfrom votes by users, higher is better938n/a
Arena rankRank 22 of 22n/a
Arena votesmore votes, a safer rating23,396n/a
GraduallyBenchour own rating, 0 to 10018n/a
GraduallyBench by task
Typography and layoutLegible text, hierarchy, and composition11n/a
Product photographyMaterials, reflections, and fine details14n/a
Character and detailAnatomy, clothing, and spatial consistency23n/a
InfographicNumbers, labels, and visual organization23n/a
API price
Per imagelower is bettern/an/a
100 imagesn/an/a
Profile
ReleasedOct 22, 2024Jan 26, 2026
Weightsopen means: runs locallyopenopen
AccessAPI, locallocal
Parameters8.1 billion80 billion
Largest output1 Megapixelnot consistently published
Plans in Germanynaming exactly this modeln/an/a

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

Sources: Stable Diffusion 3.5 Large model source (verified Aug 15, 2026) · HunyuanImage 3.0 Instruct Distil model source (verified Nov 1, 2026)

Arena ratings by category

From blind votes on LMArena. “Ahead” means the lead is clear.

No shared arena score in the stored snapshot

The stored benchmark database contains no measurement for Stable Diffusion 3.5 Large and HunyuanImage 3.0 Instruct Distil from the same arena and category. Older model versions are not used as substitutes.

Compare another matchup