FilmBench (Text-to-Video) - Aesthetic Quality: leaderboard
FilmBench (2026) scores video-generation models on prompts reverse-engineered from clips of award-winning films in 20 genres, most scripting several shots, using an automatic evaluator built with film-academy directors on a three-level cinematic-language taxonomy. This board is the aesthetic-quality axis on the 515 text-to-video prompts, covering image quality, lighting and performance, on a 0-100 scale; higher is better.
Metric: Aesthetic-quality axis score (0-100) on 515 text-to-video prompts; prompts reverse-engineered from clips of award-winning films in 20 genres, scored by the authors' expert-grade evaluation agent (Cinematic Language operators plus a judge model) on a three-level cinematic taxonomy, 1-5 per sub-metric mapped to 0-100. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Seedance 2.0 | 79 | |
| 2 | HappyHorse 1.0 | 76.9 | |
| 3 | HappyHorse 1.1 | 76.8 | |
| 4 | Kling 3.0 | 75.2 | |
| 5 | Kling 3.0 Omni | 75.1 | |
| 6 | Veo 3.1 | 73.6 | |
| 7 | Grok Imagine Video | 71.6 | |
| 8 | Vidu Q3 Pro | 70.6 | |
| 9 | Hailuo 2.3 | 62.7 |
Interactive version: theaggregate.ai/benchmark?slug=filmbench-text-to-video-aesthetic-quality · How It Works · Data refreshed daily, snapshot 2026-11-13.