Leaderboards
Video generation
Last updated: August 5, 2024Our video generation leaderboard evaluates AI models on their ability to generate high-quality videos from textual descriptions. We assess factors such as visual quality, adherence to the given text, and creativity.
Human preference evaluation
Diverse pool of US-based Alignerrs, including generalists and creative artists
Consensus of three Alignerrs per task
Standardized instructions and ontology for consistent evaluations
Carefully curated prompt generation process, balancing creativity and clarity
Consistency with prompt
Artifacts and errors
Is realistic
Examples
PROMPT
An ancient temple in the jungle with hidden traps and treasures waiting to be discovered.
Runway ML
Luma Labs
Pika