Text-to-Video Human Preferences for 5 AI Model Benchmarking

Comprising human preference data for text-to-video generation, collected via the Rapidata API in approximately 12 hours. It is used to benchmark five AI models: Sora, Hunyouan, Pika 2.0, Runway ML Alpha, and Luma Ray 2. Row and column counts are unknown.

Use Cases

• Benchmark text-to-video models like Sora and Runway ML Alpha using human preference data.
• Analyze preference patterns across the five represented models (Sora, Hunyouan, Pika 2.0, Runway ML Alpha, Luma Ray 2).
• Train a model ranking system based on the collected human preference annotations.

Strengths

• Data was collected at scale in approximately 12 hours using an accessible API.
• Contains preference data for five distinct text-to-video generation models.
• Designed specifically for benchmarking text-to-video AI models.

Limitations

• The dataset is new, with only two models initially represented, suggesting limited initial scope.
• Key structural details like row count, column names, and sample data are unavailable.
• The license, file formats, and dataset size are unknown, complicating usage assessment.

Provenance

Source

Rapidata

Collection Method

Collected using the Rapidata Python API for large-scale data annotation.

Freshness

Last updated on 2025-02-03.