VideoReasonBench

What is VideoReasonBench?

VideoReasonBench is designed to evaluate vision-centric complex video reasoning. Benchmark Radar tracks VideoReasonBench, cited by 1 source documents, with…

Released

2025-06-05

Modality

multimodal

Evaluates

强推理, Strong Reasoning, 多模态, Multimodal, video reasoning, MLLMs, 多模态模型, VLM, 逻辑推理, Reasoning, 视频理解, Video Understanding, 不支持, Unsupported

Openness

restricted

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/VideoReasonBench

VideoReasonBench paper, code and dataset

• Paper https://arxiv.org/pdf/2505.23359
• Code https://github.com/llyx97/video_reason_bench
• Dataset https://huggingface.co/datasets/lyx97/reasoning_videos

Which sources cite VideoReasonBench?

• VideoReasonBench

Related 强推理, Strong Reasoning, 多模态, Multimodal, video reasoning, MLLMs, 多模态模型, VLM, 逻辑推理, Reasoning, 视频理解, Video Understanding, 不支持, Unsupported benchmarks

• 3DCodeBench
• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• ActiveFly-Bench
• Ada-LEval
• AdvancedMathBench