Skip to main content

FLUX.1 [dev]vs.Kandinsky 3.1

Which one is better?

We have not tested Kandinsky 3.1 ourselves yet. Neither is in the arena. Neither has an API price.

Test images from GraduallyBench

Our own benchmarkThe images come from GraduallyBench, 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.

FLUX.1 [dev]: Typography and layout, first image from the fixed test run
FLUX.1 [dev]12 out of 100

No image from the four fixed tasks for Kandinsky 3.1 yet.

Kandinsky 3.1not tested yet

Result for “Typography and layout”:only FLUX.1 [dev] 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”: the 95 % ranges of both values do not overlap. “Slightly ahead”: a higher value, but the ranges overlap.

Missing image run for Kandinsky 3.1

FusionBrain timed out during our check. The public 3.1 repository demonstrates a standalone Flash pipeline, while the vendor distinguishes 3.1 from 3.1 Flash. This does not unambiguously establish execution of the complete regular 3.1 offering; Flash results are not substituted. Last checked November 2, 2026. Resolve verified access or the complete vendor pipeline for the regular 3.1 offering.

Documentation

The numbers at a glance

GraduallyBenchOur own benchmark0 to 100 · higher is better
32

FLUX.1 [dev]

Rank 76 of 108

n/a

Kandinsky 3.1

not tested yet

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

FLUX.1 [dev]

Subscription
No Black Forest Labs subscription includes this model. Through other providers from $9 a month (Krea Basic, with limited credits). 6 plans in Germany.
Via API
No API price known (access: API, local).
Weights
Open weights, Older T2I checkpoint under a non-commercial license; hosted BFL API remains documented.

Kandinsky 3.1

Subscription
n/a No plan in Germany names exactly this model.
Via API
No API price known (access: local).
Weights
Open weights.

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

GraduallyBench from Nov 7, 2026 · Subscription database from Sep 29, 2026 (40 days old)

All data side by side

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

KennzahlFLUX.1 [dev]Kandinsky 3.1
Ratings
Arena ratingfrom votes by users, higher is bettern/an/a
Arena rankn/an/a
Arena votesmore votes, a safer ratingn/an/a
GraduallyBenchour own benchmark, 0 to 10032n/a
GraduallyBench by task
Typography and layoutLegible text, hierarchy, and composition12n/a
Product photographyMaterials, reflections, and fine details41n/a
Character and detailAnatomy, clothing, and spatial consistency45n/a
InfographicNumbers, labels, and visual organization28n/a
API price
Per imagelower is bettern/an/a
100 imagesn/an/a
Profile
Releasedn/an/a
Weightsopen means: runs locallyopenOlder T2I checkpoint under a non-commercial license; hosted BFL API remains documentedopen
AccessAPI, locallocal
Parameters12 billionnot published
Largest outputnot consistently publishednot consistently published
Plans in Germanynaming exactly this model6n/a

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

Sources: FLUX.1 [dev] model source, status source (verified Nov 1, 2026) · Kandinsky 3.1 model source (verified Nov 2, 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.

No shared arena score in the stored snapshot

The stored benchmark database contains no measurement for FLUX.1 [dev] and Kandinsky 3.1 from the same arena and category. Older model versions are not used as substitutes.

More comparisons

Compare another matchup