Artificial Analysis publishes AA-Video-T2V v2.0 text-to-video benchmark prompts

Artificial Analysis has released prompts for its AA-Video-T2V v2.0 text-to-video benchmark, posted on X on 2026-10-08.

One prompt describes a 10-second product-page scene in which a presenter reveals a volcano-shaped mist diffuser, with a shift from warm daylight to dim evening lamplight, fixed close-up camera angles, and consistent presenter and product appearance across shots.

A second prompt, shared as the continuation of the set, describes a four-shot handheld documentary-style video of a glass cabin in falling snow. The shots follow a caretaker sweeping snow from the deck, empty snow-covered windows, an empty interior, and the caretaker stamping snow off his boots at the door, with hard cuts between shots. The posts describe the prompts themselves; they do not report results from any model tested against them.