NextMotionQA - Question Answering: leaderboard
Metric: Task 1 Jaccard (%) between predicted and gold option subsets on 511 multi-select four-option questions about rendered AMASS human-motion clips given to the model as RGB video (the paper headline metric for Task 1); higher is better. Source: arxiv.org. Saturation forecast: Around May 2028. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.6 Plus | 64.52 |
| 2 | Qwen 3.5 27B | 55.78 |
| 3 | GPT-5.4 Mini | 52.27 |
| 4 | InternVL3.5-8B | 48.17 |
| 5 | Qwen 3.5 9B | 47.95 |
| 6 | Qwen 3.5 4B | 44.19 |
| 7 | Qwen 3.5 0.8B | 34.24 |
Interactive version: theaggregate.ai/benchmark?slug=nextmotionqa-question-answering · How It Works · Data refreshed daily, snapshot 2026-09-29.