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

#ModelScore
1Qwen 3.6 Plus64.52
2Qwen 3.5 27B55.78
3GPT-5.4 Mini52.27
4InternVL3.5-8B48.17
5Qwen 3.5 9B47.95
6Qwen 3.5 4B44.19
7Qwen 3.5 0.8B34.24

Interactive version: theaggregate.ai/benchmark?slug=nextmotionqa-question-answering · How It Works · Data refreshed daily, snapshot 2026-09-29.