Skip to main content

GoogleKandinsky LabImage model matchup

Nano Banana 2vs.Kandinsky-5.0-T2I-Lite-Pretrain

Which one is better?

In our own benchmark GraduallyBench Image v2, Nano Banana 2 is slightly ahead, but not certainly. Kandinsky-5.0-T2I-Lite-Pretrain has no arena rating and no API price yet.

GraduallyBench Image v2Our own benchmark0 to 100 · higher is better
61

Nano Banana 2

Rank 47 of 108

25

Kandinsky-5.0-T2I-Lite-Pretrain

Rank 90 of 108

Arena ratingfrom votes by users · higher is better
1,256

Nano Banana 2

Rank 8 of 21

n/a

Kandinsky-5.0-T2I-Lite-Pretrain

not in the arena

Price per imagedollars through the API · lower is better
$0.067

Nano Banana 2

n/a

Kandinsky-5.0-T2I-Lite-Pretrain

Ranks among the 21 image models with an arena rating and the 108 with a GraduallyBench Image v2 run; prices compared with 28 models with an API price.

Test images from GraduallyBench Image v2

Our own benchmarkThe images come from GraduallyBench Image v2, 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. The task with the biggest difference is preselected.

Nano Banana 2: Typography and layout, first image from the fixed test run
Nano Banana 292 out of 100
Kandinsky-5.0-T2I-Lite-Pretrain: Typography and layout, first image from the fixed test run
Kandinsky-5.0-T2I-Lite-Pretrain9 out of 100

Result for “Typography and layout”:Nano Banana 2 ahead

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.

Test protocol of the images

Each test attempt uses the same archived prompt and one request. The first output of that attempt counts. Repeats after technical test failures are disclosed for the affected images. Files are normalized to 1,024 × 1,024 pixels without cropping. Provider resolution, randomness, quality tier and prompt processing can still differ. The images are a practical visual test, not a reconstruction of the arena configuration.

Character and detail

Nano Banana 2: together, 1024x1024, n=1, seed=provider random, provider default steps, generated Aug 14, 2026, 12:15 PM. Source

Kandinsky-5.0-T2I-Lite-Pretrain: manual, local PyTorch 2.13.0, Diffusers 0.36.0; kandinskylab/Kandinsky-5.0-T2I-Lite-pretrain-Diffusers@0df26d22e3290e9778b0471457d651a51d83ae3d; native 1024x1024, 1:1; one request, first output; steps=50, guidance=3.5, seed=893590444446603478; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoders; float32 for transformer and CPU VAE; native tokenizer truncation: CLIP 80 to 77 tokens; archived input unchanged, generated Nov 2, 2026, 8:56 PM. Source

Protocol gradually-image-comparison-v1. Prompt SHA 256: 985a75b38642a9f0e5e0c0e0c67f1b7f67780d42bd2168fa24e9a7a7a94b0da6

Nano Banana 2 image SHA 256: 5d3a70ed3fe3328484725565d9c91fb25fc7f745bd66872dae432444493a83de

Kandinsky-5.0-T2I-Lite-Pretrain image SHA 256: af9bdf8492b30fdaeb79b8f51d168a948d43ee1bbb29107f50a2f794db91a2e0

Infographic

Nano Banana 2: together, 1024x1024, n=1, seed=provider random, provider default steps, generated Aug 14, 2026, 12:15 PM. Source

Kandinsky-5.0-T2I-Lite-Pretrain: manual, local PyTorch 2.13.0, Diffusers 0.36.0; kandinskylab/Kandinsky-5.0-T2I-Lite-pretrain-Diffusers@0df26d22e3290e9778b0471457d651a51d83ae3d; native 1024x1024, 1:1; one request, first output; steps=50, guidance=3.5, seed=6008496123190594626; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoders; float32 for transformer and CPU VAE, generated Nov 2, 2026, 9:08 PM. Source

Protocol gradually-image-comparison-v1. Prompt SHA 256: ed65cb4e6a51e2336f8b149ad4cbb16e020f07d527ad94362e719d2dcf91d94f

Nano Banana 2 image SHA 256: 66123dd4e8cd5d22ecdca9cca8e4c5853a8046370aa4861ffee807a8c122c769

Kandinsky-5.0-T2I-Lite-Pretrain image SHA 256: 6d1a99203c55f6a9ba5853aae207dfc5e264adc73b336253fae874f0243bd60e

Product photography

Nano Banana 2: together, 1024x1024, n=1, seed=provider random, provider default steps, generated Aug 14, 2026, 12:15 PM. Source

Kandinsky-5.0-T2I-Lite-Pretrain: manual, local PyTorch 2.13.0, Diffusers 0.36.0; kandinskylab/Kandinsky-5.0-T2I-Lite-pretrain-Diffusers@0df26d22e3290e9778b0471457d651a51d83ae3d; native 1024x1024, 1:1; one request, first output; steps=50, guidance=3.5, seed=8854898730028115945; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoders; float32 for transformer and CPU VAE; native tokenizer truncation: CLIP 80 to 77 tokens; archived input unchanged, generated Nov 2, 2026, 8:46 PM. Source

Protocol gradually-image-comparison-v1. Prompt SHA 256: c67fd71e91304458a2feef5c91efa8677260fab0c0099a29a2c52cb579f5b2f3

Nano Banana 2 image SHA 256: 509871921c450f6f07ec28f91a380992db1b3017108fd5928fe0aa9670a1ecdc

Kandinsky-5.0-T2I-Lite-Pretrain image SHA 256: 83169f5969d6ed636c5ba8ff01236290417a5942deec1089b4725cfeb0dc2b76

Typography and layout

Nano Banana 2: together, 1024x1024, n=1, seed=provider random, provider default steps, generated Aug 14, 2026, 1:59 PM. Source

Kandinsky-5.0-T2I-Lite-Pretrain: manual, local PyTorch 2.13.0, Diffusers 0.36.0; kandinskylab/Kandinsky-5.0-T2I-Lite-pretrain-Diffusers@0df26d22e3290e9778b0471457d651a51d83ae3d; native 1024x1024, 1:1; one request, first output; steps=50, guidance=3.5, seed=9114026266664490789; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoders; float32 for transformer and CPU VAE, generated Nov 2, 2026, 8:36 PM. Source

Protocol gradually-image-comparison-v1. Prompt SHA 256: 2e012c3d14ee5dd02203a94f394ca80a5038cdebd6032b25a8b8a221f2255419

Nano Banana 2 image SHA 256: 06ae79c07d1604d3da3bbfa80bac73ac15c88af5cb8c013faaf5c9ea93092305

Kandinsky-5.0-T2I-Lite-Pretrain image SHA 256: 89cd2a1137d4d2ceb46c44b030f889bb3b14ac96ae190d2eb271dff02cfb5b74

Subscription and API

Nano Banana 2

Subscription
Free to use at Google (Google AI Free, with limited credits), more from $4.99 a month (Google AI Plus, with limited credits). Through other providers from $6 a month (ElevenLabs Starter, with limited credits). 73 plans in Germany.
Via API
$0.067 per image, 100 images $6.70.
Weights
Closed weights.

Kandinsky-5.0-T2I-Lite-Pretrain

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.

Arena rating (LMArena) from Nov 13, 2026 · GraduallyBench Image v2 from Nov 7, 2026 · API prices from Nov 12, 2026 · Subscription database from Sep 29, 2026 (48 days old)

All data side by side

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

KennzahlNano Banana 2Kandinsky-5.0-T2I-Lite-Pretrain
Ratings
Arena ratingfrom votes by users, higher is better1,256n/a
Arena rankRank 8 of 21n/a
Arena votesmore votes, a safer rating81,208n/a
GraduallyBench Image v2our own benchmark, 0 to 1006125
GraduallyBench Image v2 by task
Typography and layoutLegible text, hierarchy, and composition929
Product photographyMaterials, reflections, and fine details4551
Character and detailAnatomy, clothing, and spatial consistency4912
InfographicNumbers, labels, and visual organization5726
API price
Per imagelower is better$0.067n/a
100 images$6.70n/a
Profile
ReleasedFebruary 2026n/a
Weightsopen means: runs locallyproprietaryopen
LifecyclePrevious generation to Nano Banana 2.1; Google recommends Nano Banana 2.1 for all new projects, the stable API has existed since May 28, 2026 and no shutdown is announced, the arena entry names the earlier pre-release configurationno notice
AccessAPI, Web applocal
Parametersnot published6 billion
Largest output4Knot consistently published
Plans in Germanynaming exactly this model73n/a

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

Sources: Nano Banana 2 model source, status source (verified Aug 15, 2026) · Kandinsky-5.0-T2I-Lite-Pretrain model source (verified Nov 1, 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 Nano Banana 2 and Kandinsky-5.0-T2I-Lite-Pretrain from the same arena and category. Older model versions are not used as substitutes.

More comparisons

Compare Nano Banana 2 and Kandinsky-5.0-T2I-Lite-Pretrain with the models people compare them with most often.

Compare another matchup