Paper page - OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs

Source: https://huggingface.co/papers/2606.03890

Abstract

OVO-S-Bench presents a comprehensive benchmark for evaluating streaming spatial intelligence in multimodal language models through human-annotated questions spanning multiple abstraction levels.

Multimodal agentsin robotics, AR, andautonomous drivingmust reason about places and layouts from continuousegocentric streams, often using evidence outside the current view. Existing benchmarks either evaluate offline over full videos or target events rather than spatial structure. We introduce OVO-S-Bench, a fully human-annotated benchmark forstreaming spatial intelligence, comprising 1,680 questions over 348 source videos. Annotation involves 12 trained annotators, each also serving as a blind cross-reviewer, across roughly 804 person-hours of multi-round quality assurance. Each question carries a query timestamp and an evidence interval, and at evaluation, the model sees only the prefix preceding the query. Questions span four levels of increasing abstraction: instantaneous egocentric perception, spatiotemporal context tracking, spatial simulation and reasoning, andallocentric mapping. Across 38 proprietary and open-source MLLMs, Gemini-3.1-Pro trails human experts by 27 points, 59.2 vs. 86.6, withallocentric mappingas the dominant bottleneck. Notably, streaming and spatially fine-tuned MLLMs underperform their own backbones. We further find thatchain-of-thought reasoningamplifies spatial errors when ungrounded in the stream. By exposing these limitations, OVO-S-Bench establishes a demanding testbed for next-generation streaming spatial MLLMs.

View arXiv pageView PDFProject pageGitHub30Add to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2606.03890 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2606.03890 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2606.03890 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.