Pith. sign in

REVIEW 17 cited by

Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.16103 v2 pith:XXFWB3KD submitted 2023-11-27 cs.CV cs.AI

classification cs.CVcs.AI
keywords video-llmsbenchmarktoolkitvideo-benchcomprehensioncomprehensiveevaluatingmodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Video-based large language models (Video-LLMs) have been recently introduced, targeting both fundamental improvements in perception and comprehension, and a diverse range of user inquiries. In pursuit of the ultimate goal of achieving artificial general intelligence, a truly intelligent Video-LLM model should not only see and understand the surroundings, but also possess human-level commonsense, and make well-informed decisions for the users. To guide the development of such a model, the establishment of a robust and comprehensive evaluation system becomes crucial. To this end, this paper proposes \textit{Video-Bench}, a new comprehensive benchmark along with a toolkit specifically designed for evaluating Video-LLMs. The benchmark comprises 10 meticulously crafted tasks, evaluating the capabilities of Video-LLMs across three distinct levels: Video-exclusive Understanding, Prior Knowledge-based Question-Answering, and Comprehension and Decision-making. In addition, we introduce an automatic toolkit tailored to process model outputs for various tasks, facilitating the calculation of metrics and generating convenient final scores. We evaluate 8 representative Video-LLMs using \textit{Video-Bench}. The findings reveal that current Video-LLMs still fall considerably short of achieving human-like comprehension and analysis of real-world videos, offering valuable insights for future research directions. The benchmark and toolkit are available at: \url{https://github.com/PKU-YuanGroup/Video-Bench}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 17 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing

    cs.CV 2025-06 conditional novelty 7.0 of 10

    SAVVY-Bench tests audio-visual LLMs on dynamic 3D spatial questions, and the SAVVY pipeline, combining visual tracks with spatial audio and global mapping, lifts Gemini-2.5-pro accuracy from 50.9% to 58.0%.

  2. Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint Frames

    cs.CV 2025-05 conditional novelty 7.0 of 10

    A new egocentric benchmark shows vision-language models fail at spatial reasoning across disjoint frames, falling 28 points behind humans and only improving sharply when handed ground-truth 3D coordinates.

  3. AdsQA: Towards Advertisement Video Understanding

    cs.CV 2025-09 conditional novelty 6.0 of 10

    AdsQA adds an ad-video question-answering benchmark and ReAd-R, a GRPO-trained model that beats 7B baselines but not larger closed models.

  4. MESH -- Understanding Videos Like Human: Measuring Hallucinations in Large Video Models

    cs.CV 2025-09 conditional novelty 6.0 of 10

    MESH, a three-layer video hallucination benchmark, shows LVMs ace basic objects and coarse traits but slip badly on fine character details and multi-subject actions in longer clips.

  5. VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A person-anchored tree plus multi-agent LLM pipeline lets a system answer cross-video queries about the same person, and it beats single-video models on the authors' new CrossVideoQA benchmark.

  6. VLM4D: Towards Spatiotemporal Awareness in Vision Language Models

    cs.CV 2025-08 unverdicted novelty 6.0 of 10

    VLM4D benchmarks spatiotemporal reasoning in VLMs and finds large gaps versus humans, with proposed methods showing partial improvement.

  7. "Harmless to You, Hurtful to Me!": Investigating the Detection of Toxic Languages Grounded in the Perspective of Youth

    cs.CL 2025-08 unverdicted novelty 6.0 of 10

    The authors construct the first Chinese youth-toxicity dataset, show that youth and adult perceptions of toxic language diverge, and report that adding contextual meta information improves detection accuracy.

  8. GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them?

    cs.CV 2025-07 conditional novelty 6.0 of 10

    Introduces GLIMPSE, a video-QA benchmark whose questions cannot be answered from single frames; best model GPT-o3 scores 66.43% vs 94.82% human accuracy.

  9. VRBench: A Benchmark for Multi-Step Reasoning in Long Narrative Videos

    cs.CV 2025-06 conditional novelty 6.0 of 10

    VRBench is a benchmark of 960 long narrative videos with 8,243 human-written multi-step questions, plus a two-level evaluation of answer accuracy and reasoning quality for 31 large models.

  10. MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks

    cs.CV 2025-06 conditional novelty 6.0 of 10

    AVHaystacks is a new 3100-question benchmark for audio-visual QA across 500 videos, and the MAGNET multi-agent pipeline beats current baselines on it.

  11. VideoConviction: A Multimodal Benchmark for Human Conviction and Stock Market Recommendations

    cs.MM 2025-06 conditional novelty 6.0 of 10

    VideoConviction provides the first expert-annotated multimodal benchmark of financial influencer video recommendations, showing MLLMs extract tickers better but struggle with actions and conviction, and that an invers...

  12. VUDG: A Dataset for Video Understanding Domain Generalization

    cs.CV 2025-05 conditional novelty 6.0 of 10

    VUDG is a domain-generalization benchmark for video understanding with 11 domains and 36,388 QA pairs, and it shows that current large video-language models lose accuracy across visual domains.

  13. TimeCausality: Evaluating the Causal Ability in Time Dimension for Vision Language Models

    cs.CV 2025-05 conditional novelty 6.0 of 10

    Introduces a 700-pair benchmark for temporal causal reasoning in VLMs, revealing large open-source vs. closed-source gaps and strong position bias.

  14. NeMo: Needle in a Montage for Video-Language Understanding

    cs.CV 2025-09 conditional novelty 5.0 of 10

    NeMoBench, an automatically generated benchmark with 31,378 QA pairs, shows that video LLMs struggle with temporal grounding of relevant clips hidden in long montages.

  15. Iterative Zoom-In: Temporal Interval Exploration for Long Video Understanding

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A confidence-guided iterative zoom-in framework improves long-video question answering for multimodal LLMs without any training.

  16. VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos

    cs.CV 2025-05 conditional novelty 5.0 of 10

    A new benchmark, VF-Eval, measures how well multimodal LLMs check, detect, and reason about errors in AI-generated videos, and shows frontier models remain far below human performance.

  17. CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step

    cs.CV 2025-07 conditional novelty 4.0 of 10

    CoT-Diff couples a multimodal LLM's step-by-step 3D layout reasoning into the diffusion denoising loop, claiming large gains in spatial alignment for text-to-image generation.

Pith tools