Image & vision

Artificial Analysis Video Arena (AA-Video-T2V)

by Artificial Analysis

What is Artificial Analysis Video Arena (AA-Video-T2V)? Artificial Analysis Video Arena (AA-Video-T2V) is an image & vision eval made by Artificial Analysis. A live human-preference Elo leaderboard for generated video. Blind pairwise votes (including audio on the with-sound boards) produce separate text-to-video, image-to-video and editing rankings. On 14 Nov 2026 the AA-Video-T2V v2.1 board listed 34 models, with Wan 3.0 first at Elo 1175.13 (7,787 appearances), and the page labelled '7 models added in the last 30 days'. This is a preference arena, not an automatic physics or quality suite. Rankings change with votes; re-read the live board before quoting any Elo or order.

Page last updated 2026-10-18 · Evals Review

Editor note

A live human-preference Elo leaderboard for generated video. Blind pairwise votes (including audio on the with-sound boards) produce separate text-to-video, image-to-video and editing rankings. On 14 Nov 2026 the AA-Video-T2V v2.1 board listed 34 models, with Wan 3.0 first at Elo 1175.13 (7,787 appearances), and the page labelled '7 models added in the last 30 days'. This is a preference arena, not an automatic physics or quality suite. Rankings change with votes; re-read the live board before quoting any Elo or order.

What it tests
Blind human preference for text-to-video, image-to-video and video editing, scored with Elo.
Original source
artificialanalysis.ai/video/arena
Last updated
Leaderboard snapshotted 2026-11-14 18:23 IST
License
Not checked yet — see source

Facts come only from the linked source (checked 15–16 Oct 2026). Credit belongs to the creators. We don't score or rank evals: how we review.

Reviews

No reviews yet.

Reviews are written by people who sign in with GitHub, one per account per eval. We can't confirm that each reviewer used the eval; we remove reviews that break our rules, never just for being negative, and we never add, buy or edit reviews. Averages, when shown, come only from these reviews.

Sign in with GitHub to review

Related image & vision evals

  • MMMU — Expert-level multimodal understanding and reasoning.
  • MathVista — Mathematical reasoning over figures, plots and images.
  • MMBench — Broad perception and reasoning skills of vision-language models.
  • ChartQA — Question answering over charts.

All Image & vision evals · Comparison table

Discussion

No one has discussed Artificial Analysis Video Arena (AA-Video-T2V) yet. Have you run it? Share what it caught, what it missed or how you set it up.

Sign in with GitHub to comment

Be specific and kind. No promotion or affiliate links. Community rules · All discussions