Artificial Analysis: Gemini Omni 1.2 Flash takes #2 on its video-editing leaderboard

Artificial Analysis (which calls the model Gemini Omni Flash 1.2) says it ranks #2 on AA-Video-Editing v1.1. Against Omni 1.1 it moves from #12 to #6 on AA-Video-T2V v2.1 (text to video) and from #17 to #14 on AA-Video-I2V v2.1 (image to video).

In its testing, Artificial Analysis says the model does best on dialogue scenes, multi-shot stories and UI and motion-design clips in text to video, and on complex edits and visual effects in editing. It says the model is weaker at human anatomy and at sound and speech edits.

Artificial Analysis puts the price at $6.26 per minute of 1080p video on the Gemini API, 31% less than Omni 1.1 at $9.12 per minute. It says the model replaces Omni 1.1 on the Gemini API on December 3, and that it is available in the Gemini API, Google AI Studio, Vertex AI, the Gemini app, Google Flow and YouTube. These are Artificial Analysis's figures and findings.