Paper Detail

Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains

Diandian Zhang, Tingyu Song, Lin Fu, Zheyuan Yang, Yilun Zhao

arxiv Score 12.2

Published 2026-08-10 · First seen 2026-08-11

General AI

Abstract

We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation across scientific domains. It contains 1,253 expert-annotated examples spanning 60 subjects across four core disciplines: Natural Science, Healthcare, Humanities & Social Sciences, and Engineering. Each example requires models to generate temporally rich videos that demand scientific reasoning and knowledge-grounded synthesis, going beyond surface-level visual plausibility. We further establish a rubric-based evaluation protocol. Our analysis shows that, under this protocol, both non-expert human evaluators and MLLM-as-Judge systems can achieve relatively high agreement with expert judgments, supporting reproducible evaluation at scale. We benchmark 16 frontier proprietary and open-source models and find that, while automatic perceptual-quality scores cluster tightly across systems, performance on Prompt Grounding and Scientific and Causal Correctness varies substantially, with a pronounced proprietary-open-source gap. These findings show that advances in visual realism have not yet translated into reliable modeling of scientific and causal dynamics.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{zhang2026sci,
  title = {Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains},
  author = {Diandian Zhang and Tingyu Song and Lin Fu and Zheyuan Yang and Yilun Zhao},
  year = {2026},
  abstract = {We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation across scientific domains. It contains 1,253 expert-annotated examples spanning 60 subjects across four core disciplines: Natural Science, Healthcare, Humanities \& Social Sciences, and Engineering. Each example requires models to generate temporally rich videos that demand scientific reasoning and knowledge-grounded synthesis, going beyond surface-level visual plausibility. We fu},
  url = {https://arxiv.org/abs/2608.09873},
  keywords = {cs.CV, cs.AI, code available, huggingface daily},
  eprint = {2608.09873},
  archiveprefix = {arXiv},
}

Metadata

{}