WBench - Interaction: leaderboard
Metric: Score (0-100): the mean of navigation, event editing, subject action and perspective switching, text-driven models only, multi-turn generation; higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kling 3.0 | 73.1 |
| 2 | Wan 2.7 | 72.1 |
| 3 | Seedance 1.5 | 68.3 |
| 4 | HY-Video 1.5 | 54.7 |
| 5 | LTX 2.3 | 49.3 |
| 6 | YUME 1.5 | 48.4 |
| 7 | LongCat-Video | 45.1 |
| 8 | Cosmos 2.5 | 43.5 |
| 9 | Kairos 3.0 | 41.6 |
Interactive version: theaggregate.ai/benchmark?slug=wbench-interaction · How It Works · Data refreshed daily, snapshot 2026-10-07.