NextMotionQA - Error Correction: leaderboard
Metric: Task 3 caption error correction score (0-100): mean of error-span identification, token recall against the gold span and Gemini-judged correctness of the rewrite, on 400 captions of rendered AMASS human-motion clips given to the model as RGB video; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.6 Plus | 65.25 |
| 2 | Qwen 3.5 27B | 62.85 |
| 3 | Qwen 3.5 4B | 56.35 |
| 4 | Qwen 3.5 9B | 52.34 |
| 5 | InternVL3.5-8B | 51.19 |
| 6 | GPT-5.4 Mini | 43.57 |
| 7 | Qwen 3.5 0.8B | 11.41 |
Interactive version: theaggregate.ai/benchmark?slug=nextmotionqa-error-correction · How It Works · Data refreshed daily, snapshot 2026-09-29.