MotionHalluc - Temporal Hallucination: leaderboard
Choosing which of three reference clips is in the same action phase as the query clip (316 questions). MotionHalluc (Guo et al., 2026) tests whether multimodal models compare a query and a reference fitness-exercise video (553 pairs from Fit3D) without hallucinating motion differences; open models decode greedily and API models are averaged over three runs. Accuracy in percent; higher is better.
Metric: Accuracy (%; pick the reference clip, of three, in the same action phase as the query clip; 316 questions). Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3.5 Plus | 68.03 | #227 |
| 2 | Gemini 3 Flash | 53.05 | #159 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=motionhalluc-temporal-hallucination · How It Works · Data refreshed daily, snapshot 2026-11-12.