NextMotionQA: leaderboard
Metric: Overall score (0-100): macro-average of the three task scores (Task 1 mean of accuracy, Jaccard and precision; Task 2 captioning mean; Task 3 correction mean) on rendered AMASS human-motion clips given to the model as RGB video; higher is better. Source: arxiv.org. Saturation forecast: Around March 2028. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.6 Plus | 54.85 |
| 2 | Qwen 3.5 27B | 49.75 |
| 3 | Qwen 3.5 4B | 42.36 |
| 4 | GPT-5.4 Mini | 42.33 |
| 5 | Qwen 3.5 9B | 42 |
| 6 | InternVL3.5-8B | 41.82 |
| 7 | Qwen 3.5 0.8B | 20.34 |
Interactive version: theaggregate.ai/benchmark?slug=nextmotionqa · How It Works · Data refreshed daily, snapshot 2026-09-29.