Wan 3.0 takes first place in video editing with audio on the AA arena
- Source
- Artificial Analysis
- Date
Wan 3.0 debuts at #1 on the Artificial Analysis Video Editing Leaderboard, and is a close #2 in Text to Video with Audio Wan 3.0 is Alibaba's new all-in-one video generation and editing model, positioned as a single system for turning multimodal creative direction into video. It generates up to 30 seconds at 1080p with native audio and accepts text, images, video, audio, documents, and web pages as creative references. The same model supports Text to Video, Image to Video, reference-based generation, and instruction-led editing, including changes to visuals, plot, dialogue, and sound. In the Artificial Analysis Video Arena, Wan 3.0 ranks #1 in Video Editing with Audio, #2 in Text to Video with Audio, and #5 in Image to Video with Audio. Wan 3.0 marks a large generational improvement: against the most recent Wan 2.7 version on each leaderboard, it rises from #5 to #1 in Video Editing with Audio, #6 to #2 in Text to Video with Audio, and #12 to #5 in Image to Video with Audio. Wan 3.0 is available now in public preview through Alibaba Cloud Model Studio. Pricing starts at $0.05 per second for 480p, increasing to $0.10 for 720p and $0.20 for 1080p. Congratulations to @Alibaba_Wan and @alibaba_cloud on the release! See below for comparisons between Wan 3.0 and other leading models in the Artificial Analysis Video Arena 🧵
Text to Video (With Audio) Prompt: A cat staring at its own reflection in a toaster, paw tapping the chrome surface. The distorted cat reflection taps back. Audio: Paw taps, confused meow.
Image to Video (With Audio) Prompt: Dragon spreads its wings, lifts off, and flies across the sky with powerful wingbeats. Tail trails behind as it soars into the distance. Heavy wings flapping, deep roar, and rushing wind.
Video Editing (With Audio) Prompt: Restyle the cat's fisheye POV into a hand-drawn cartoon look while keeping the first-person motion.
Context
Alibaba launched Wan 3.0 in public preview on August 24, 2026, doubling its predecessor's clip length to 30 seconds at up to 1080p and adding native audio by default. The same model handles text-to-video, image-to-video, and instruction-led editing of an existing video's visuals, dialogue, or sound, accepting text, images, video, audio, or documents as reference material.
Artificial Analysis, which runs independent human-voted arenas for these models, ranks Wan 3.0 first in video editing with audio and a close second in text-to-video with audio, up from fifth and sixth respectively for the prior Wan 2.7 release on the same leaderboards. Pricing on Alibaba Cloud Model Studio starts at $0.05 per second at 480p, rising to $0.20 per second at 1080p.
Checking sign-in…
Loading comments…