Skip to main content

RunwayOpenMOSSImage model matchup

Runway Gen-4 Imagevs.MOSS-Image-Base

Which one is better?

In our own benchmark GraduallyBench Image v2, MOSS-Image-Base leads. Neither is in the arena. Neither has an API price.

GraduallyBench Image v2Our own benchmark0 to 100 · higher is better
32

Runway Gen-4 Image

Rank 75 of 108

58

MOSS-Image-Base

Rank 48 of 108

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.

Runway Gen-4 Image: Character and detail, first image from the fixed test run
Runway Gen-4 Image25 out of 100
MOSS-Image-Base: Character and detail, first image from the fixed test run
MOSS-Image-Base69 out of 100

Result for “Character and detail”:MOSS-Image-Base ahead

Prompt given to both modelsCreate 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.

What the rating looks at: Anatomy, clothing, and spatial consistency.

“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

Runway Gen-4 Image: manual, 1:1, one request, first output (first top-left candidate of native batch), exact UI model Runway Gen-4 Image, provider-default random seed, native resolution provider default, fast mode not offered, no reference images, no selected effects, default content settings, source UI file Firefly_Create a square cinematic full-body portrait of a fictional bicycle courier waiting u 715099.png, source 1080x1080, stored 1024x1024 (Lanczos3 downscale), generated Nov 1, 2026, 10:33 PM. Source

MOSS-Image-Base: manual, local PyTorch 2.13.0, Diffusers 0.41.0; OpenMOSS-Team/MOSS-Image-Base@85975793d8b3d432f1b6e27f352abaa4c2a4c0d3; native 1024x1024, 1:1; one request, first output; steps=50, guidance=3.0, seed=921965437095743280; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoder and transformer; float32 for VAE; unconditional skip layers=[22]; CPU operator fallback permitted, actual fallback use was not measured; official experimental MPS compatibility runtime OpenMOSS/MOSS-Image@1961ca3d111b828e65278656cde0c8f94484f4dd, generated Nov 2, 2026, 10:39 PM. Source

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

Runway Gen-4 Image image SHA 256: 1235971dc0ffbe1e82ce305c9e7608d10a9b604697ec359a332cd4f2d931db71

MOSS-Image-Base image SHA 256: 313d95f3e7766e861d46b0563c81bb2a02782708004c24c7aab0c46e8587ff83

Infographic

Runway Gen-4 Image: manual, 1:1, one request, first output (first top-left candidate of native batch), exact UI model Runway Gen-4 Image, provider-default random seed, native resolution provider default, fast mode not offered, no reference images, no selected effects, default content settings, source UI file Firefly_Create a square German infographic titled SO FUNKTIONIERT PHOTOSYNTHESE. Show exactly 715099.png, source 1080x1080, stored 1024x1024 (Lanczos3 downscale), generated Nov 1, 2026, 10:33 PM. Source

MOSS-Image-Base: manual, local PyTorch 2.13.0, Diffusers 0.41.0; OpenMOSS-Team/MOSS-Image-Base@85975793d8b3d432f1b6e27f352abaa4c2a4c0d3; native 1024x1024, 1:1; one request, first output; steps=50, guidance=3.0, seed=2567672344276262662; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoder and transformer; float32 for VAE; unconditional skip layers=[22]; CPU operator fallback permitted, actual fallback use was not measured; official experimental MPS compatibility runtime OpenMOSS/MOSS-Image@1961ca3d111b828e65278656cde0c8f94484f4dd, generated Nov 2, 2026, 10:43 PM. Source

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

Runway Gen-4 Image image SHA 256: 13955a0ff71a8e54cde4d84a78ace5dba2bc64b8df79c939bffabca22620480c

MOSS-Image-Base image SHA 256: 3175582007cf377490ab51f73a57ebddb312f523ac5bfb54ae7598e72eb3edca

Product photography

Runway Gen-4 Image: manual, 1:1, one request, first output (first top-left candidate of native batch), exact UI model Runway Gen-4 Image, provider-default random seed, native resolution provider default, fast mode not offered, no reference images, no selected effects, default content settings, source UI file Firefly_Create a square premium product photograph of a brushed titanium wristwatch standing 715099.png, source 1080x1080, stored 1024x1024 (Lanczos3 downscale), generated Nov 1, 2026, 10:31 PM. Source

MOSS-Image-Base: manual, local PyTorch 2.13.0, Diffusers 0.41.0; OpenMOSS-Team/MOSS-Image-Base@85975793d8b3d432f1b6e27f352abaa4c2a4c0d3; native 1024x1024, 1:1; one request, first output; steps=50, guidance=3.0, seed=8912274556852986311; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoder and transformer; float32 for VAE; unconditional skip layers=[22]; CPU operator fallback permitted, actual fallback use was not measured; official experimental MPS compatibility runtime OpenMOSS/MOSS-Image@1961ca3d111b828e65278656cde0c8f94484f4dd, generated Nov 2, 2026, 10:35 PM. Source

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

Runway Gen-4 Image image SHA 256: 24a4b7e7c9ac88d5e5c7a508aca6c7de29c4ca9e55c0d17623005dbe3e6aaadd

MOSS-Image-Base image SHA 256: af9ea47eb1554bcaaaadf8860fecfa5bb69095a58bf346e3d9a73be8240a2a7c

Typography and layout

Runway Gen-4 Image: manual, 1:1, one request, first output (first top-left candidate of native batch), exact UI model Runway Gen-4 Image, provider-default random seed, native resolution provider default, fast mode not offered, no reference images, no selected effects, default content settings, source UI file Firefly_Create a square editorial poster for an imaginary night train called MONDFALTER. Show 715099.png, source 1080x1080, stored 1024x1024 (Lanczos3 downscale), generated Nov 1, 2026, 10:31 PM. Source

MOSS-Image-Base: manual, local PyTorch 2.13.0, Diffusers 0.41.0; OpenMOSS-Team/MOSS-Image-Base@85975793d8b3d432f1b6e27f352abaa4c2a4c0d3; native 1024x1024, 1:1; one request, first output; steps=50, guidance=3.0, seed=9219943416610765538; mps for text encoder and denoising; cpu for native VAE decode; bfloat16 for text encoder and transformer; float32 for VAE; unconditional skip layers=[22]; CPU operator fallback permitted, actual fallback use was not measured; official experimental MPS compatibility runtime OpenMOSS/MOSS-Image@1961ca3d111b828e65278656cde0c8f94484f4dd, generated Nov 2, 2026, 10:31 PM. Source

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

Runway Gen-4 Image image SHA 256: 73ca9e031f19143e8227ccfb5d651cd72eed23184d7cf7b980890310d55f7a8d

MOSS-Image-Base image SHA 256: e87b1d9d7aa09487c6b9be505746dacb2f3be551f29a5d85424a44a2a88089c5

Subscription and API

Runway Gen-4 Image

Subscription
No Runway subscription includes this model. Through other providers from $6 a month (ElevenLabs Starter, with limited credits). 19 plans in Germany.
Via API
No API price known (access: API, Web app).
Weights
Unknown.

MOSS-Image-Base

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 Image v2 from Nov 7, 2026 · Subscription database from Sep 29, 2026 (45 days old)

All data side by side

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

KennzahlRunway Gen-4 ImageMOSS-Image-Base
Ratings
Arena ratingfrom votes by users, higher is bettern/an/a
Arena rankn/an/a
Arena votesmore votes, a safer ratingn/an/a
GraduallyBench Image v2our own benchmark, 0 to 1003258
GraduallyBench Image v2 by task
Typography and layoutLegible text, hierarchy, and composition4558
Product photographyMaterials, reflections, and fine details3058
Character and detailAnatomy, clothing, and spatial consistency2569
InfographicNumbers, labels, and visual organization2947
API price
Per imagelower is bettern/an/a
100 imagesn/an/a
Profile
Releasedn/aOct 16, 2026
Weightsopen means: runs locallyunknownopen
AccessAPI, Web applocal
Parametersnot published5 billion
Largest outputnot consistently publishednot consistently published
Plans in Germanynaming exactly this model19n/a

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

Sources: Runway Gen-4 Image model source (verified Nov 1, 2026) · MOSS-Image-Base 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 Runway Gen-4 Image and MOSS-Image-Base from the same arena and category. Older model versions are not used as substitutes.

More comparisons

Compare Runway Gen-4 Image and MOSS-Image-Base with the models people compare them with most often.

Compare another matchup