Benchmark

LENS Benchmark

What is LENS?

A multi-level evaluation benchmark of multimodal reasoning with with 3.4K contemporary images and 60K+ human-authored questions covering eight tasks and 12…

Released: 2025-06-01
Modality: multimodal
Evaluates: 多模态, Multimodal, 推理, Reasoning, 视觉问答, Visual-Qa, 物理智能, Embodied AI, 逻辑推理, 图像理解, Image Understanding, 空间理解, Spatial Understanding, 不支持, Unsupported
Openness: unknown
Importer: OpenCompass Hub
Reported scores: 0

Source provenance

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

LENS paper, code and dataset

Paper https://arxiv.org/abs/2505.15616
Code https://github.com/mars2workshop/LENS
Dataset https://huggingface.co/datasets/zhihe678/LENS

No reported scores are on record for this benchmark yet.

Which sources cite LENS?

LENS

Related 多模态, Multimodal, 推理, Reasoning, 视觉问答, Visual-Qa, 物理智能, Embodied AI, 逻辑推理, 图像理解, Image Understanding, 空间理解, Spatial Understanding, 不支持, Unsupported benchmarks