FilmBench (Text-to-Video) - Temporal Continuity: leaderboard
Metric: Temporal-continuity 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 |
|---|---|---|
| 1 | Seedance 2.0 | 96.1 |
| 2 | HappyHorse 1.1 | 94.8 |
| 3 | Kling 3.0 Omni | 94.7 |
| 4 | Kling 3.0 | 94.6 |
| 5 | HappyHorse 1.0 | 94.5 |
| 6 | Veo 3.1 | 90.4 |
| 7 | Vidu Q3 Pro | 90.1 |
| 8 | Grok Imagine Video | 89 |
| 9 | Hailuo 2.3 | 88.1 |
Interactive version: theaggregate.ai/benchmark?slug=filmbench-text-to-video-temporal-continuity · How It Works · Data refreshed daily, snapshot 2026-09-29.