Is Runway Gen-4.5 better than Kling 3.0?

Gen-4.5 leads on Artificial Analysis's blind preference benchmark. Kling 3.0 leads on features — multi-shot storyboards, 15-second clips, and native audio in six languages. The better model depends on what your project requires.

Can I use Runway Agent on PonPon?

Runway Agent is exclusive to Runway's platform. PonPon offers its own AI agent that orchestrates across 30+ models, routing each generation step to the best-suited engine rather than limiting output to a single model family.

What are Runway Characters used for?

Real-time conversational avatars for customer support, training, advertising, and gaming. Any image becomes a live video agent that lip-syncs and gestures during conversation at 24fps with under two seconds of latency.

Should I switch to Runway or stay multi-model?

If you want workflow simplicity and only need Runway's model quality, the integrated stack is compelling. If you want the best output for each specific shot type, access to all leading models through one interface gives you more flexibility.

← すべての投稿

2026年5月19日 · PonPon Team

Runway's May 2026 Triple Launch

Gen-4.5 claimed #1 on Video Arena. Agent turns conversations into finished films. Characters makes any image a live avatar.

Runway shipped three distinct products in May 2026, each targeting a different layer of the video creation stack. Gen-4.5 competes on raw generation quality. Runway Agent competes on workflow automation. Runway Characters competes on real-time interactive media. Together, they represent the most aggressive single-month expansion any AI video company has attempted.

The timing is not accidental. With Sora gone and Google's Gemini Omni still months from public access, the competitive window is wide. Runway is using it to redefine what an AI video platform is — from a generation tool to an autonomous creative partner.

Gen-4.5: Number One on Video Arena

Gen-4.5 launched to immediate benchmark dominance, claiming the #1 position on Artificial Analysis's Video Arena with an Elo score of 1,247. The model beat every competitor in blind human-preference testing — evaluators watched pairs of clips and selected the output they preferred, with no knowledge of which model produced which clip.

The quality improvements are specific and measurable. Objects move with realistic weight and momentum. Liquids flow with accurate fluid dynamics. Surface materials — metal, fabric, glass, skin — render with texture detail that previous models approximated but never matched. Physical causality tracks correctly: a ball hitting water produces a splash proportional to its mass and velocity, not a generic splash effect.

Gen-4.5 supports text-to-video, image-to-video, and video-to-video generation. Pricing runs from $15/month on Standard to $95/month for Unlimited, positioning it as a premium tool rather than a mass-market play.

The benchmark lead, however, comes with context. still offers multi-shot storyboard sequences that Gen-4.5 lacks — the ability to generate six consistent camera cuts in a single pass. still leads on camera control fidelity, where directorial prompts like "slow dolly left while tracking the subject" execute with more precision. Benchmark scores measure preference on isolated clips; production workflows care about features beyond single-clip quality.

Runway Agent: From Conversation to Finished Video

Released May 13, Runway Agent is a conversational interface that handles the full video production pipeline: concept development, story beats, visual direction, multi-scene generation, voiceover, dialogue, music, and final assembly. The user describes what they need. The agent proposes a direction. Together they iterate until the agent generates a ready-to-publish video.