MODEL Runway Last updated:

Runway Gen-4.5

Video Arena Leader

Runway's December 2025 video model — currently leads the Artificial Analysis text-to-video arena. Excels at multi-shot storytelling (the same character across cuts), camera motion control, and the "Act-One" feature that drives a generated character with a recorded human performance.

Why it matters

Set the bar for "production-grade" AI video — the standard against which Sora 2, Veo 3.1, and Chinese contenders (Kling, Seedance, Hailuo) are judged. Established that AI video can be a cinematographic tool, not just a TikTok clip generator.

Core Capabilities

Generative
Produces images, video, audio, or other media.
Multimodal
Combines text, vision, and audio in one model.
Vision
Understands images, scenes, and visual context.

Context Window

Context window not disclosed.

Availability

API
Available
Product / App
Available
Open Source
Not released
Enterprise
Contact sales

Pricing Model

Subscription
Bundled inside the host product.
Subscription

Capability / Performance

Where this model sits relative to the middle 60% of models in the tree. All scores are 0–10 (higher is better).

Lower 20% Upper 80% This model
Lower 20% 20th percentile — 20% of models score below this This model Where the current model lands Upper 80% 80th percentile — only 20% of models score above this Percentile boundaries are computed across every model in the tree that reports the underlying benchmark for each capability.

What it feels like

  • Vision-language model from Runway — see the linked sources below for benchmark and review coverage
  • Vision and multimodal tasks are the typical fit per the published model card

Best use cases

  • Vision tasks (charts, documents, images) per the model card
  • See the model spec and sources block for benchmarked use cases

Tools to try

Not ideal for

  • Tasks far outside the modalities listed in this model's spec
  • Workflows where a more recent successor in the same family scores higher

Runway Research