mindcube
Datasets
All datasets matching “mindcube”MindCube_lmmseval
MindCube LMMs Eval Dataset
This dataset is formatted for use with lmms-eval framework.
Dataset Schema
Column
Type
Description
id
string
Unique identifier for each sample (format: {split}_{scene_id}_{question_id})
category
list[string]
Category labels (e.g., ["perpendicular", "P-O", "meanwhile", "self"])
type
string
Question type (e.g., "1_frame", "2_frame", "3_frame", "general")
meta_info
list[list[string]]
Metadata about scene objects and their spatial… See the full description on the dataset page: https://huggingface.co/datasets/oscarqjh/MindCube_lmmseval.MindCube
MindCube: Spatial Mental Modeling from Limited Views
MindCube is a novel benchmark designed to evaluate how well Vision Language Models (VLMs) can form robust spatial mental models from limited visual views. It comprises 21,154 questions across 3,268 images, assessing capabilities such as cognitive mapping (representing positions), perspective-taking (orientations), and mental simulation (dynamics for "what-if" movements). The dataset aims to expose critical gaps in existing VLMs'… See the full description on the dataset page: https://huggingface.co/datasets/MLL-Lab/MindCube.MindCube-TinyBench
MindCube TinyBench Evaluation Dataset
This package contains the MindCube TinyBench split used for MindCube evaluation in PhysBrainEvalKit. It is a compact evaluation-only subset for reproducible testing of vision-language models on spatial mental modeling tasks.
Contents
MindCube-TinyBench/
├── data/
│ ├── raw/
│ │ └── MindCube_tinybench.jsonl
│ └── other_all_image/
│ └── <referenced image files>
└── README.md
The split contains 1,050 questions and… See the full description on the dataset page: https://huggingface.co/datasets/VLyb/MindCube-TinyBench.mindcube-latent-data
MindCube reasoning traces (text)
Self-distilled map-then-reason chain-of-thought traces for the
MindCube spatial-VLM benchmark. This repo ships plain text
only — the raw reasoning traces. It contains no pre-compressed / tokenized targets, so it is
useful as-is for any reasoning-distillation setup.
Contents
file
rows
what
native_maptrace_full.jsonl
7,474
Frozen Qwen2.5-VL-3B-Instruct, run greedily on MindCube spatial questions (the aug_cgmap_ffr_out… See the full description on the dataset page: https://huggingface.co/datasets/leapeto/mindcube-latent-data.mindcube_resultsMindCube-20kRaw data in .parquet format from this repo.