Human-Level Accuracy, Non-Human Strategies: Revealing Model-Human Divergence in Video Physical Reasoning

Abstract

Video foundation models now reach human-level accuracy on physical-reasoning benchmarks, yet such tasks require predicting unobserved physical outcomes. Do these models perform human-like forward simulation, or do they exploit statistical regularities in visible scenes? Accuracy alone cannot distinguish these strategies. We introduce a distributional evaluation framework that treats model seeds and human raters as populations, enabling comparison of consensus, uncertainty, and strategy. On the Physion benchmark, we evaluate three ViT-L architectures (V-JEPA2, VideoMAEv2, DINOv2). V-JEPA2 narrows the accuracy gap to ~1 percentage point (73.2% vs. 74.2%), yet model-human disagreement reaches 26.4%, far exceeding human-human disagreement (4.8%), with substantially lower agreement (kappa ~ 0.48 vs. 0.91). The divergence follows forward-simulation demands: models outperform humans on geometric reasoning (linking, +11.8 pp) but underperform on gravitational dynamics (rolling, -11.8 pp) and causal chains (dominoes, -10.5 pp). Strategy fingerprinting confirms all three architectures share non-human strategies while none aligns with humans. Attribution analysis suggests that unobservable outcome features, rather than visible scene properties, predict this divergence, consistent with models relying more on scene-level statistical regularities than on explicit forward simulation, a systematic divergence that accuracy alone cannot reveal. Code is available at https://github.com/fanhong-li/model-human-divergence.