datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
apex-agents
APEX–Agents
APEX–Agents is a benchmark from Mercor for evaluating whether AI agents can execute long-horizon, cross-application professional services tasks. Tasks were created by investment banking analysts, management consultants, and corporate lawyers, and require agents to navigate realistic work environments with files and tools (e.g., docs, spreadsheets, PDFs, email, chat, calendar).
Tasks: 480 total (160 per job category)
Worlds: 33 total (10 banking, 11 consulting, 12… See the full description on the dataset page: https://huggingface.co/datasets/mercor/apex-agents.ParseBench
ParseBench
Quick links: [🌐 Website] [📜 Paper] [💻 Code]
ParseBench is a benchmark for evaluating document parsing systems on real-world enterprise documents, with the following characteristics:
Multi-dimensional evaluation. The benchmark is stratified into five capability dimensions — tables, charts, content faithfulness, semantic formatting, and visual grounding — each with task-specific metrics designed to capture what agentic workflows depend on.
Real-world enterprise… See the full description on the dataset page: https://huggingface.co/datasets/llamaindex/ParseBench.turkey-all-universitiesCertainly! Here’s the dataset description in Markdown format:
All Universities in Turkey Dataset
Description
This dataset contains detailed information about various universities. Each record represents a single university and includes attributes such as the university's name, type, city, website, address, logo URL, and a button for accessing additional details. This data is typically extracted from a web page listing universities.
Fields
1. id… See the full description on the dataset page: https://huggingface.co/datasets/h8st6ptv/turkey-all-universities.ExtractBench
ExtractBench
Quick links: [🌐 Website] [📜 Paper] [💻 Code]
Given a document and a schema, a system returns structured data with evidence. The input is a full document, born-digital or scanned, and a schema written by the user. The output is a schema-valid JSON object, with the source page and a bounding box for each value as evidence. It must return correct, exhaustive values (including repeated records), correctly use null for absent information, and ground each extracted… See the full description on the dataset page: https://huggingface.co/datasets/llamaindex/ExtractBench.VQAonline
VQAonline
🌐 Homepage | 🤗 Dataset | 📖 arXiv
Dataset Description
We introduce VQAonline, the first VQA dataset in which all contents originate from an authentic use case.
VQAonline includes 64K visual questions sourced from an online question answering community (i.e., StackExchange).
It differs from prior datasets; examples include that it contains:
(1) authentic context that clarifies the question
(2) an answer the individual asking the question validated as… See the full description on the dataset page: https://huggingface.co/datasets/ChongyanChen/VQAonline.cadgenbench-submissions
CADGenBench Submissions
Submissions and evaluation results for the CADGenBench leaderboard.
Leaderboard Space: HuggingAI4Engineering/CADGenBench.
Benchmark code: github.com/huggingface/cadgenbench.
Fixture inputs: HuggingAI4Engineering/cadgenbench-data.
Ground truth: HuggingAI4Engineering/cadgenbench-data-gt (private).
Contents
Path
What it is
results.jsonl
One row per submitted + evaluated submission. The leaderboard table reads from this.… See the full description on the dataset page: https://huggingface.co/datasets/HuggingAI4Engineering/cadgenbench-submissions.MVBench
MVBench
Important Update
[18/10/2024] Due to NTU RGB+D License, 320 videos from NTU RGB+D need to be downloaded manually. Please visit ROSE Lab to access the data. We also provide a list of the 320 videos used in MVBench for your reference.
We introduce a novel static-to-dynamic method for defining temporal-related tasks. By converting static tasks into dynamic ones, we facilitate systematic generation of video tasks necessitating a wide range of temporal abilities, from… See the full description on the dataset page: https://huggingface.co/datasets/OpenGVLab/MVBench.M3_VOS
[CVPR 2025] M3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation
If you like our project, please give us a star ⭐ on GitHub for the latest update.
💡 Description
Venue: CVPR2025
Repository: 🛠️Tool, 🏠Page
Paper: arxiv.org/html/2412.13803v2
Point of Contact: Jiaxin Li , Zixuan Chen
📁 Structure
This dataset contains annotated videos and images for object segmentation tasks with phase transition information. The directory… See the full description on the dataset page: https://huggingface.co/datasets/Lijiaxin0111/M3_VOS.Finch
Finch (FinWorkBench): Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows
This repository contains the dataset for Finch, an enterprise-grade benchmark for evaluating an agent’s ability to work like a skilled finance & accounting expert (work IQ) on real-world professional workflows.
Paper: https://arxiv.org/abs/2512.13168
Evaluation Code: https://github.com/FinWorkBench/Finch
🍻 Updates
2026-4-6: FinWorkBench is accepted to ACL… See the full description on the dataset page: https://huggingface.co/datasets/FinWorkBench/Finch.eMCR
eMCR: A Benchmark for Multi-Condition Product Retrieval in Chinese E-Commerce
This is the official dataset and evaluation code for the paper "eMCR: A Benchmark for Multi-Condition Product Retrieval in Chinese E-Commerce".
Overview
Product search increasingly involves queries that combine multiple requirements — product attributes, brands, prices, exclusions, and visual descriptions. Existing retrieval benchmarks provide limited support for diagnosing which… See the full description on the dataset page: https://huggingface.co/datasets/alibabagroup/eMCR.CrossVid
CrossVid: A Comprehensive Benchmark for Evaluating Cross-Video Reasoning in Multimodal Large Language Models
Dataset Description
CrossVid is a large-scale, multi-task dataset designed to advance cross-video understanding capabilities in vision-language models. The dataset encompasses 10 diverse task types that require models to reason across multiple videos, understand temporal dynamics, spatial relationships, and complex narrative structures. Unlike existing benchmarks… See the full description on the dataset page: https://huggingface.co/datasets/Chuntianli/CrossVid.ChartDiff
ChartDiff: A Large-Scale Benchmark for Comprehending Pairs of Charts
Overview
ChartDiff is a large-scale benchmark for cross-chart comparative summarization, designed to evaluate whether vision-language models can identify differences and generate coherent comparative descriptions across pairs of charts.
Unlike existing chart understanding datasets that emphasize single-chart interpretation, ChartDiff requires models to compare two charts jointly and generate a concise… See the full description on the dataset page: https://huggingface.co/datasets/ckchaos/ChartDiff.ShareGPT4Video
ShareGPT4Video 4.8M Dataset Card
Dataset details
Dataset type:
ShareGPT4Video Captions 4.8M is a set of GPT4-Vision-powered multi-modal captions data of videos.
It is constructed to enhance modality alignment and fine-grained visual concept perception in Large Video-Language Models (LVLMs) and Text-to-Video Models (T2VMs). This advancement aims to bring LVLMs and T2VMs towards the capabilities of GPT4V and Sora.
sharegpt4video_40k.jsonl is generated by GPT4-Vision… See the full description on the dataset page: https://huggingface.co/datasets/ShareGPT4Video/ShareGPT4Video.RoboPulsePlusPlus
RoboPulse++
RoboPulse++ is an interval-level benchmark introduced in PRM-as-a-Judge 1.5: A Toolkit for Robot Process Assessment for evaluating progress judge models throughout complete robot manipulation trajectories.
This Hugging Face release contains 700 episodes with natural-language task instructions, temporally ordered observations, and human-annotated progress intervals.
Overview
RoboPulse++ extends progress judging from isolated state pairs to temporal… See the full description on the dataset page: https://huggingface.co/datasets/lyy0715/RoboPulsePlusPlus.SpineBench
Dataset Card for SpineBench
Benchmark Details
Paper Information
Benchmark Examples
Benchmark Distribution
Data Format
Data SourceHuman Evaluation of MLLMs Reasoning Performance
Citation
Benchmark Details
SpineBench is a comprehensive Visual Question Answering (VQA) benchmark designed for fine-grained analysis and evaluation of LVLM in the spinal domain. SpineBench comprises 64,878 QA pairs from 40,263 spine images, covering 11 spinal diseases through two critical… See the full description on the dataset page: https://huggingface.co/datasets/Silversorrow/SpineBench.MedXpertQA
Dataset Card for MedXpertQA
MedXpertQA is a highly challenging and comprehensive benchmark designed to evaluate expert-level medical knowledge and advanced reasoning capabilities. It features both text-based and multimodal question-answering tasks, with the multimodal subset leveraging structured clinical information alongside images.
Dataset Description
MedXpertQA comprises 4,460 questions spanning diverse medical specialties, tasks, body systems, and image types. It… See the full description on the dataset page: https://huggingface.co/datasets/TsinghuaC3I/MedXpertQA.flat-pack-bench
Flat-Pack Bench 🧩
Furniture assembly as a spatio-temporal stress test for large vision-language models.
Flat-Pack Bench is a multiple-choice benchmark for evaluating fine-grained
spatio-temporal understanding in real furniture assembly videos. Each question
asks a model to reason about object parts, contact events, assembly order, final
connectivity, or part identity across time.
Project page: https://flat-pack-bench.github.io
🎯 Benchmark Tasks
The benchmark… See the full description on the dataset page: https://huggingface.co/datasets/justachetan/flat-pack-bench.VOST-TAS
[NeurIPS 2025] Tracking and Understanding Object Transformations
If you like our project, please give us a star ⭐ on GitHub for the latest update.
💡 Description
Dataset Visualizations: GitHub
Paper: arXiv:2511.04678
Project Page: tubelet-graph.github.io
Project Repository: GitHub
Point of Contact: Yihong Sun
📊 Dataset Overview
VOST-TAS (TrackAnyState) is an extended version of the VOST validation set with explicit transformation annotations for tracking and… See the full description on the dataset page: https://huggingface.co/datasets/yihongs/VOST-TAS.hateful_memes_expandedRoadmapBench
RoadmapBench
A benchmark for evaluating AI coding agents on multi-target, long-horizon software development tasks derived from open-source project version upgrades.
Overview
RoadmapBench contains 115 tasks spanning 17 open-source repositories across 5 programming languages (Python, TypeScript, Go, Rust, C++). Each task requires an agent to implement multiple interdependent features that correspond to a real version upgrade of the target project.
Quick Start… See the full description on the dataset page: https://huggingface.co/datasets/UnipatAI/RoadmapBench.FormStruct-Bench
FormStruct-Bench
Dataset Description
FormStruct-Bench is a multilingual benchmark for extracting the semantic and
spatial structure of forms from document images. The repository combines a
7,000-page main benchmark, a controlled visual-degradation set, and
template-level layout annotations. It supports evaluation of vision-language
models and document AI systems on hierarchical key-value extraction, document
structure recovery, region localization, table and… See the full description on the dataset page: https://huggingface.co/datasets/D2I-CUHK-Shenzhen/FormStruct-Bench.svgrepo
Dataset Card for SVGRepo Icons
Dataset Summary
This dataset contains a large collection of Scalable Vector Graphics (SVG) icons sourced from SVGRepo.com. The icons cover a wide range of categories and styles, suitable for user interfaces, web development, presentations, and potentially for training vector graphics or icon classification models. Each icon is provided under a specific open-source or permissive license, clearly indicated in its metadata. The SVG… See the full description on the dataset page: https://huggingface.co/datasets/nyuuzyou/svgrepo.PKLot
PKLot: Parking Space Occupancy Detection Dataset
Unofficial redistribution of the PKLot parking-lot database, reformatted into a standardized YOLO-compatible detection layout, under the original CC BY 4.0 license.
Disclaimer
This repository is not an official release of the PKLot dataset.
PKLot was created by Paulo R. L. de Almeida, Luiz S. Oliveira, Alceu S. Britto Jr, Eunelson J. Silva Jr, and Alessandro L. Koerich, and is distributed by the Vision… See the full description on the dataset page: https://huggingface.co/datasets/dronefreak/PKLot.IndustryBench-MIPU
IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products
Multi-Image Industrial Product Understanding Benchmark — evaluating MLLMs on structured attribute extraction from real-world industrial product images.
Industrial product specifications are scattered across multiple heterogeneous images — specification tables, nameplates, technical drawings. IndustryBench-MIPU tests whether MLLMs can reliably recover them through four… See the full description on the dataset page: https://huggingface.co/datasets/alibaba-multimodal-industrial-ai/IndustryBench-MIPU.Motion-o-MCoT-PLM-motion-keyframes
Motion-o-MCoT (PLM + motion keyframes)
Subset of STGR: STR_plm_rdcap rows with <motion in reasoning_process, plus sharded keyframes under videos/stgr/plm/kfs/.
Train split: 3,168 examples (see export_manifest.json in the repo for exact export stats).
Keyframes: JPEGs are stored under shard subfolders (e.g. videos/stgr/plm/kfs/plm_0150/…) so each directory stays under Hugging Face file-count limits. Each key_frames[].path in the JSON is relative to videos/stgr/plm/kfs/ (e.g.… See the full description on the dataset page: https://huggingface.co/datasets/bishoygaloaa/Motion-o-MCoT-PLM-motion-keyframes.Qwen-Image-Bench
Qwen-Image-Bench
A creator-centric benchmark for evaluating Text-to-Image models beyond semantic alignment.
Links
Resource
Link
📑 Paper
http://arxiv.org/abs/2605.28091
📊 Benchmark Dataset (HuggingFace)
https://huggingface.co/datasets/Qwen/Qwen-Image-Bench
📊 Benchmark Dataset (ModelScope)
https://www.modelscope.cn/datasets/Qwen/Qwen-Image-Bench
💻 GitHub
https://github.com/QwenLM/Qwen-Image-Bench
🧑⚖️ Q-Judger Model… See the full description on the dataset page: https://huggingface.co/datasets/Qwen/Qwen-Image-Bench.PuzzleWorld
Dataset Card for PuzzleWorld
PuzzleWorld is a benchmark of 667 real-world puzzlehunt–style problems designed to evaluate open-ended, multimodal reasoning capabilities of AI models. Curated from Puzzled Pint’s Creative Commons–licensed archives (2010–2025), each puzzle combines text, visual, and structured inputs with no explicitly stated instructions. Solvers must first infer the hidden problem structure from ambiguous clues and then execute a multi-step, creative reasoning… See the full description on the dataset page: https://huggingface.co/datasets/hzli1202/PuzzleWorld.DBvstar_benchMAP-CC
MAP-CC
🌐 Homepage | 🤗 MAP-CC | 🤗 CHC-Bench | 🤗 CT-LLM | 📖 arXiv | GitHub
An open-source Chinese pretraining dataset with a scale of 800 billion tokens, offering the NLP community high-quality Chinese pretraining data.
Disclaimer
This model, developed for academic purposes, employs rigorously compliance-checked training data to uphold the highest standards of integrity and compliance. Despite our efforts, the inherent complexities of data and the broad spectrum of… See the full description on the dataset page: https://huggingface.co/datasets/m-a-p/MAP-CC.