Runway Gen-4 Image

Released
2025-05-16
Last refreshed
2026-05-19
Status
Researched 174d ago
ProprietaryCommercial use: restrictedMultimodal

Runway Gen-4 Image is a released general LLM work model; evaluate it while provider pricing coverage matures.

Specifications
Released
2025-05-16
Specialization
image-generation
Openness
Proprietary
License
ProprietaryRestricted
Weights
Not released
Code
Unknown
Created by

Democratizing video creation through AI

New York City, New York, United States
Founded 2018
Website
Pricing

No tracked provider pricing is available yet.

About

Runway Gen-4 Image by Runway. A production text-to-image model supporting reference image generation for character and location consistency across scenes. Released to API May 16, 2025, part of the broader Gen-4 creative AI family (released March 31, 2025). Available on Replicate (runwayml/gen4-image) and Runway API.

Providers

No active provider routes are tracked for this model yet.

Capabilities

Multimodal

Benchmark peer barsfor Coding

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(1)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
1,024text_to_image overall 2026-10-26Observed 2026-10-27
Configuration: Runway Gen-4
Harness: LMArena blind pairwise human votes, Bradley-Terry
Evaluator: LMArena
Confidence: confirmed
Notes: LMArena text to image leaderboard, overall category, published 2026-10-26 (HF lmarena-ai/leaderboard-dataset @a467e6b9, latest split). Board entry 'Runway Gen-4': rank 71 of 82, Arena Score 1023.8 (95% CI 1019.4-1028.2), 54330 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.

Migration checks

No linked migration route is available for this model yet.