SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models

arXiv 2026 24.1 benchmark

TLDR

Introduces SpaceCast-Bench, a benchmark of 3,862 questions from 182 real-world scenes evaluating predictive spatial reasoning in vision-language models, revealing a large gap versus humans.

Reasoning

The paper presents a novel diagnostic benchmark with progressive task levels, extensive model evaluation, and useful controlled analyses. However, the abstract does not discuss limitations or potential biases in the programmatically generated training data.

Read-first score

Read-first score 24.1, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 26.

Recency 5%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Topical relevance 25%

37.1

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Methodology quality 15%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark

Reproducibility 15%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Graph prestige 15%

5.7

PageRank-style prestige over the local citation graph built from available OpenAlex references. local_pagerank=0.0016

Citation impact 15%

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. cited_by_count=0

Citation velocity 10%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 187.

Keyword Scores

world dynamics prediction

world model

world simulator

generative world model

interactive world model

video world model

model-based reinforcement learning world model

Resources

Paper