FilmBench (Text-to-Video) - Instruction Following: 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 instruction-following axis on the 515 text-to-video prompts, covering shot, camera and staging directions, on a 0-100 scale; higher is better.
Metric: Instruction-following 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 | 91.7 | |
| 2 | HappyHorse 1.1 | 90.7 | |
| 3 | HappyHorse 1.0 | 89.5 | |
| 4 | Kling 3.0 Omni | 88.3 | |
| 5 | Kling 3.0 | 87.5 | |
| 6 | Vidu Q3 Pro | 82 | |
| 7 | Grok Imagine Video | 82 | |
| 8 | Veo 3.1 | 78.5 | |
| 9 | Hailuo 2.3 | 55.9 |
Interactive version: theaggregate.ai/benchmark?slug=filmbench-text-to-video-instruction-following · How It Works · Data refreshed daily, snapshot 2026-11-13.