Skip to content
UtilPick.
My toolbox
All tools
Favorites
Saved tools

불러오는 중…

Recently used

열어 본 도구가 여기에 표시돼요.

Get the desktop app
Settings
UtilPick.
All tools
All tools/Video Generation AI Ranking

Video Generation AI Ranking

Compare text-to-video and image-to-video AI models by blind human-vote arena rankings (silent-video leaderboard), refreshed daily.

Loading the tool…

User reviews

No reviews yet. If you’ve used this tool, be the first to leave one.

User reviews

No reviews yet.

Write a review

Checking your sign-in status…

    How to use

    1. 01

      Choose text-to-video or image-to-video

    2. 02

      See every model lined up in a five-rank army, from Sergeant to Recruit, by its position

    3. 03

      See the top 30 in the table and use Replay to watch how first place changed month by month

    How it works and good to know

    Once a day the server fetches the Artificial Analysis video arena ranking; the date is shown at the top. If it can’t be fetched, the built-in ranking and its date are shown. Scores are Elo ratings from blind votes between two videos made from the same prompt; differences of a few dozen points are effectively a tie. Price, generation speed, resolution and clip length are not part of the score. Release dates are known only to the month, and Replay redraws the race by release month using today’s Elo. Logos refer to each company’s trademarks; UtilPick is not affiliated with any of them.

    Related tools

    View all
    Image Generation AI RankingImages
    AI Model LeaderboardDeveloper
    Subtitle EditorVideo & Audio
    © 2026 UtilPickSimple tools for a complicated day. A free collection of online utilities.Get the desktop appAbout UtilPick Request a toolReport a problem
    Privacy Policy (Korean)Terms of Use (Korean)Contact[email protected]

    Today’s leaders

    • Today’s changes…
    01

    Video AI squad

    Fetching the latest rankings…

    Text to video
    Image to video
    Elo score from blind votes between two videos generated from the same promptHigher is betterSource Artificial Analysis

    Sergeant Wan 3.0 · 1335

    Ranks by position · cut at the top 10, 30, 55 and 80%

    1. Sergeant

      Leads the squad

      #1–3 · Elo 1335–1302

    2. Corporal

      The backbone right behind the sergeants

      #4–12 · Elo 1286–1230

    3. Private First Class

      The steady middle of the line

      #13–18 · Elo 1225–1215

    4. Private

      Still catching up at the back

      #19–24 · Elo 1214–1210

    5. Trainee

      Fresh recruits in the last row

      #25–30 · Elo 1209–1193

    Today’s changes

    Daily rankings are collected and compared with yesterday

    Rankings started collecting today. From tomorrow, rises, drops and new entries compared with yesterday appear here.

    02

    Ranking table

    Elo score from blind votes between two videos generated from the same prompt · Higher is better · click a model name to see every benchmark

    Swipe the table sideways to see more columns.

    AI model ranking by Text to video, as of 2026-09-29
    RankModelCompanyEloReleased
    1Alibaba13352026-08
    2Google DeepMind13322026-05
    3MiniMax13022026-07
    4Alibaba-ATH12862026-04
    5Alibaba-ATH12722026-06
    6ByteDance Seed12592026-03
    7Alibaba12432026-06
    8xAI12352026-01
    9KlingAI12302026-02
    9KlingAI12302026-02
    9PixVerse12302026-02
    9PixVerse12302026-03
    Show sources and method
    As of
    2026-09-29 · source data is fetched and re-ranked once a day
    Source
    • Artificial Analysistext to video and image to video arena Elo scores, release months and replay races. Fetched once a day
    Reading Elo scores
    People compare two results made from the same prompt without knowing which model made them and pick the better one; the winner gains points and the loser loses them. Because it’s a relative score built from votes, a 100-point gap means the leading model wins about 64% of head-to-heads, and gaps of a few dozen points are effectively a tie. Price, generation speed and resolution and clip length are not part of the score.
    Reading the army
    All models in the current benchmark (up to 30) are placed into five ranks by position: the top 10% are Sergeants, up to 30% Corporals, up to 55% Privates First Class, up to 80% Privates, and the rest Recruits. Video Elo scores are tightly packed, so ranks go by position rather than score gaps. A model tied in Elo with the last one in a higher rank joins that rank. Check each rank’s Elo range for the real differences. The company filter only picks which soldiers to show; it doesn’t change ranks.
    Release month and NEW
    Artificial Analysis reports releases only to the month, so months are shown. NEW is counted from the 1st of that month and given only to models certainly released within 30 days of the reference date. Different quality settings (high, max, etc.) of the same model are ranked separately.
    Replay
    A race redrawn with today’s Elo, placing only the models released up to each month. These are not the scores from back then.
    Trademarks
    Logos and characters refer to each company’s trademarks, which belong to their owners. UtilPick is not affiliated with, sponsored or endorsed by any of them. Logo icons: Lobe Icons (MIT).
    Other AI rankingsAI Model LeaderboardImage Generation AI Ranking