MORSE-500 Benchmark

What is MORSE-500?

MORSE-500 introduces 500 programmatically generated videos testing 6 reasoning types: abstract, physical, planning, spatial, temporal, mathematical. Its…

Released

2025-06-05

Modality

multimodal

Evaluates

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

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

• Original evidence https://hub.opencompass.org.cn/dataset-detail/MORSE-500

MORSE-500 paper, code and dataset

• Paper https://arxiv.org/abs/2506.05523
• Code https://github.com/morse-benchmark/morse-500
• Dataset https://huggingface.co/datasets/video-reasoning/morse-500
• Dataset https://huggingface.co/datasets/video-reasoning/morse-500-view

Which sources cite MORSE-500?

• MORSE-500

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

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