Wan 3.0 leads AA-Video-T2V v2.0’s text-to-video rankings
Artificial Analysis says its new benchmark judges clips at 1080p, with prompts tagged by use case, capability and visual style. It also launched a version for video generated without audio.
TLDR
Artificial Analysis says AA-Video-T2V v2.0 draws on more than 68,000 human preference votes across 1,000 prompts. Its initial rankings put Wan 3.0 first overall and atop 10 of 20 category boards, followed by Dreamina Seedance 2.5 and MiniMax H3 (768p). It lists MiniMax H3 at $4.80 per minute, compared with $34.12 for Seedance 2.5. A separate silent benchmark draws on more than 47,000 votes across 500 prompts.
Combined views
22.6K
11 Sources, first seen 3h ago