Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
Abstract
Video-Holmes benchmark evaluates complex video reasoning capabilities of MLLMs using suspense short films and reveals significant challenges in information integration compared to human experts.
Recent advances in CoT reasoning and RL post-training have been reported to enhance video reasoning capabilities of MLLMs. This progress naturally raises a question: can these models perform complex video reasoning in a manner comparable to human experts? However, existing video benchmarks primarily evaluate visual perception and grounding abilities, with questions that can be answered based on explicit prompts or isolated visual cues. Such benchmarks do not fully capture the intricacies of real-world reasoning, where humans must actively search for, integrate, and analyze multiple clues before reaching a conclusion. To address this issue, we present Video-Holmes, a benchmark inspired by the reasoning process of Sherlock Holmes, designed to evaluate the complex video reasoning capabilities of MLLMs. Video-Holmes consists of 1,837 questions derived from 270 manually annotated suspense short films, which spans seven carefully designed tasks. Each task is constructed by first identifying key events and causal relationships within films, and then designing questions that require models to actively locate and connect multiple relevant visual clues scattered across different video segments. Our comprehensive evaluation of state-of-the-art MLLMs reveals that, while these models generally excel at visual perception, they encounter substantial difficulties with integrating information and often miss critical clues. For example, the best-performing model, Gemini-2.5-Pro, achieves an accuracy of only 45%, with most models scoring below 40%. We aim that Video-Holmes can serve as a "Holmes-test" for multimodal reasoning, motivating models to reason more like humans and emphasizing the ongoing challenges in this field. The benchmark is released in https://github.com/TencentARC/Video-Holmes.
Community
Video-Holmes
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning (2025)
- ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models (2025)
- VCRBench: Exploring Long-form Causal Reasoning Capabilities of Large Video Language Models (2025)
- LENS: Multi-level Evaluation of Multimodal Reasoning with Large Language Models (2025)
- VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning (2025)
- VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge (2025)
- GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 1
Spaces citing this paper 0
No Space linking this paper