arXiv:2610.38103 · v1

The Prestige: Benchmarking Cognitive Visual Reasoning using Magic Tricks

首次提交 2026-10-28 08:41

版本更新 2026-10-28 08:41

雷达观测 2026-10-30 10:23

摘要

We introduce The Prestige, a video understanding benchmark that probes cognitive visual reasoning through professional magic performances, where deliberate misdirection challenges models to track events and explain unexpected outcomes. The benchmark comprises open-ended questions ranging from temporal and causal understanding to robustness against adversarial questions. Evaluation of leading open-source and proprietary VLMs reveals a substantial gap between even the strongest model and human performance. We also find systematic discrepancies between human and automated grading and identify recurring model failure modes. Ablations further show that models can select correct multiple-choice answers even when they fail to generate correct explanations independently, motivating further investigations into question formats. Together, these findings highlight limitations in both VLM reasoning and its evaluation, underscoring the need for more reliable video understanding models and more rigorous benchmarks.

作者备注：40th Conference on Neural Information Processing Systems (NeurIPS 2026). Track on Evaluations and Datasets