datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
benchmark-bcpluswds_objectnethot3d
HOT3D-Clips
This Hugging Face repository hosts HOT3D-Clips, a set of curated sub-sequences of the HOT3D dataset.
Download instructions for HOT3D-Clips and the full HOT3D dataset can be found here.
See HOT3D Toolkit for documentation of the data format and for Python utilities (for loading, undistorting fisheye images, rendering using fisheye cameras, etc.).
More details can be found in the HOT3D paper and BOP 2024 report.
RoadmapBench
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.
Task Structure… See the full description on the dataset page: https://huggingface.co/datasets/benchmark-anon-2026/RoadmapBench.wds_imagenet_sketchexplicit-edit-benchmark
Explicit Edit Benchmark
226 deterministic exact-edit tasks, run by different agents, harnesses, models and configurations. Every observation records what the harness did and whether the resulting files matched byte for byte.
Source code and benchmark runner: GitHub — Explicit Edit Benchmark
Open the interactive Explorer to compare agents, harnesses, models, versions, reasoning modes, correctness, recovery, time, cost and tokens.
Leaderboard by model route
Score v2… See the full description on the dataset page: https://huggingface.co/datasets/alexshpunt/explicit-edit-benchmark.MultiBanana-Benchmark🍌 MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation 🍌
CVPR 2026 (Main)
This repository provides the datasets for
“MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation” by Yuta Oshima, Daiki Miyake, Kohsei Matsutani, Yusuke Iwasawa, Masahiro Suzuki, Yutaka Matsuo and Hiroki Furuta
Paper Link
https://arxiv.org/abs/2511.22989
Github Repository
For the usage of this benchmark, please see Github… See the full description on the dataset page: https://huggingface.co/datasets/kohsei/MultiBanana-Benchmark.dojo_benchmark_kline
Languages: 简体中文 · English
dojo_benchmark_kline — Benchmark Index Bars
Overview
Daily OHLCV for major broad and representative indices across US, CN, and HK (e.g. ^SPX, ^HSI, 000300.SS). Each row is one index on one trade date.
Files
File
Description
data.parquet
Index daily bars
Key Fields
Field
Description
symbol
Index code (e.g. ^SPX, 000300.SS)
kline_t
Bar interval; "1D" for daily bars
bar_time… See the full description on the dataset page: https://huggingface.co/datasets/AlphaDojo/dojo_benchmark_kline.frames-benchmark
FRAMES: Factuality, Retrieval, And reasoning MEasurement Set
FRAMES is a comprehensive evaluation dataset designed to test the capabilities of Retrieval-Augmented Generation (RAG) systems across factuality, retrieval accuracy, and reasoning.
Our paper with details and experiments is available on arXiv: https://arxiv.org/abs/2409.12941.
Dataset Overview
824 challenging multi-hop questions requiring information from 2-15 Wikipedia articles
Questions span diverse topics… See the full description on the dataset page: https://huggingface.co/datasets/google/frames-benchmark.BLINK
BLINK: Multimodal Large Language Models Can See but Not Perceive
🌐 Homepage | 💻 Code | 📖 Paper | 📖 arXiv | 🔗 Eval AI
This page contains the benchmark dataset for the paper "BLINK: Multimodal Large Language Models Can See but Not Perceive"
Introduction
We introduce BLINK, a new benchmark for multimodal language models (LLMs) that focuses on core visual perception abilities not found in other evaluations. Most of the BLINK tasks can be solved by humans “within a… See the full description on the dataset page: https://huggingface.co/datasets/BLINK-Benchmark/BLINK.Video-MME-v2
🔥 News
2026.06.11 Videos re-encoded to H265, maintaining consistent evaluation scores. Fixed 2 incorrect MP4s & 3 mismatched URLs. Original data preserved in the original branch.
2026.05.22 Task types are now available for Q1-Q3 in coherence (logic) groups.
🤗 About This Repo
This repository contains annotation data for "Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding". It mainly consists of three… See the full description on the dataset page: https://huggingface.co/datasets/MME-Benchmarks/Video-MME-v2.daytrader-benchmarkssai-osworld-v2-benchmark-runs
Sai on OSWorld-V2 — benchmark runs of record
Two complete 108-task runs of the Sai computer-use agent on OSWorld-V2, with full
per-task evidence: scores, trajectories, agent runtime logs, evaluator logs, API
protocol logs, and run manifests.
Run
Date
Tasks scored
Mean score
Perfect (1.0)
Zeros
run1/
2026-08-12
108/108
0.7276
28
7
run2/
2026-08-20
108/108
0.7329
33
5
Model anthropic/claude-opus-5, thinking max, --max_steps 500, screenshot-only
observation… See the full description on the dataset page: https://huggingface.co/datasets/simular-ai/sai-osworld-v2-benchmark-runs.GAIA
GAIA dataset
GAIA is a benchmark which aims at evaluating next-generation LLMs (LLMs with augmented capabilities due to added tooling, efficient prompting, access to search, etc).
We added gating to prevent bots from scraping the dataset. Please do not reshare the validation or test set in a crawlable format.
Data and leaderboard
GAIA is made of more than 450 non-trivial question with an unambiguous answer, requiring different levels of tooling and autonomy to… See the full description on the dataset page: https://huggingface.co/datasets/gaia-benchmark/GAIA.wds_imagenet-rUMI-Benchmark-v1
UMI-Benchmark-v1
UMI-Benchmark-v1 contains 20,000 real-world robot manipulation sessions across 10 tasks:
4 single-arm tasks and 6 dual-arm tasks.
Dataset Summary
Category
Tasks
Sessions
Single-arm
4
9,988
Dual-arm
6
10,012
Total
10
20,000
Tasks
ID
Folder
Type
Task
Sessions
T1
single_arm_task1
Single-arm
Stack Baskets
3,000
T2
single_arm_task2
Single-arm
Trash Bag
1,991
T3
single_arm_task3
Single-arm
Stamp Ink
2… See the full description on the dataset page: https://huggingface.co/datasets/UMIbenchmark/UMI-Benchmark-v1.svg-benchmark
Rapidata Static SVG Generation Benchmark
Built by Rapidata.
This dataset contains 1,918,367 human responses, collected with the
Rapidata Python SDK, comparing how well 42 frontier LLMs generate
static SVGs from text prompts. Each row is a head-to-head comparison between two models' renders of
the same prompt, scored by human annotators on one of three questions (Preference, Coherence, Alignment).
The SVGs are produced as raw <svg> markup by the models, rasterized to 768×768 PNGs… See the full description on the dataset page: https://huggingface.co/datasets/Rapidata/svg-benchmark.wds_imagenet-ahendrycks-MATH-benchmark
Hendrycks MATH Dataset
Dataset Description
The MATH dataset is a collection of mathematics competition problems designed to evaluate mathematical reasoning and problem-solving capabilities in computational systems. Containing 12,500 high school competition-level mathematics problems, this dataset is notable for including detailed step-by-step solutions alongside each problem.
Dataset Summary
The dataset consists of mathematics problems spanning multiple… See the full description on the dataset page: https://huggingface.co/datasets/nlile/hendrycks-MATH-benchmark.what-ai-benchmarks-actually-measure
What AI Benchmarks Actually Measure: Item-Level Model Outputs and Scores for 53 Models
Item-level model responses and scores for 53 language models across the
56 benchmarks analyzed in What AI Benchmarks Actually Measure: Adapting
Convergent and Discriminant Validity to Interrogate Fifty-Six AI Benchmarks
(Desai et al., 2026,
arxiv.org/abs/2609.08812).
We do not release the prompts from the benchmark datasets, but instead refer to them by
item ids. To regenerate the prompts from… See the full description on the dataset page: https://huggingface.co/datasets/madesai/what-ai-benchmarks-actually-measure.wds_imagenetv2wds_imagenet1kregx-benchmark
RegX
Cross-Domain Multi-View Point Cloud Registration Benchmark
RegX evaluates multi-view point cloud registration across scales spanning nine orders
of magnitude — nanometre-scale microscopy to kilometre-scale airborne maps — and sensors
never designed to be compared: clinical colonoscopes, RGB-D cameras, spinning and
solid-state LiDAR, terrestrial and airborne laser scanners.
Most registration benchmarks fix one sensor and one scale. RegX asks a narrower question
instead: does… See the full description on the dataset page: https://huggingface.co/datasets/YuePanEdward/regx-benchmark.pdfQA-Benchmark
pdfQA: Diverse, Challenging, and Realistic Question Answering over PDFs
pdfQA is a structured benchmark collection for document-level question answering and PDF understanding research.
The dataset is organized to support:
Raw document processing research
Structured extraction pipelines
Retrieval-augmented QA
End-to-end document reasoning systems
It preserves original documents alongside structured derivatives to enable reproducible evaluation across preprocessing strategies.… See the full description on the dataset page: https://huggingface.co/datasets/pdfqa/pdfQA-Benchmark.megaposeloom-benchmark-mmlu-promHumanEval-Benchmark
🔷 Accepted in NAACL Proceedings (2025) 🔷
mHumanEval
The mHumanEval benchmark is curated based on prompts from the original HumanEval 📚 [Chen et al., 2021]. It includes a total of 33,456 prompts for Python, and 836,400 in total - significantly expanding from the original 164.
Quick Start
Detailed… See the full description on the dataset page: https://huggingface.co/datasets/md-nishat-008/mHumanEval-Benchmark.multi_task_multi_modal_knowledge_retrieval_benchmark_M2KR
PreFLMR M2KR Dataset Card
Dataset details
Dataset type:
M2KR is a benchmark dataset for multimodal knowledge retrieval. It contains a collection of tasks and datasets for training and evaluating multimodal knowledge retrieval models.
We pre-process the datasets into a uniform format and write several task-specific prompting instructions for each dataset. The details of the instruction can be found in the paper. The M2KR benchmark contains three types of tasks:… See the full description on the dataset page: https://huggingface.co/datasets/BByrneLab/multi_task_multi_modal_knowledge_retrieval_benchmark_M2KR.STRABLE-benchmark
STRABLE: Benchmarking Tabular Machine Learning with Strings
This dataset card describes the STRABLE benchmark, a comprehensive suite designed for evaluating machine learning models on tabular data containing strings.
Dataset Description
Benchmarking tabular data has revealed the benefit of dedicated architectures, pushing the state of the art. However, real-world tables often contain string entries beyond pure numbers, a setting that has been understudied due to a… See the full description on the dataset page: https://huggingface.co/datasets/inria-soda/STRABLE-benchmark.cvdp-benchmark-datasetImportant please see "Files and versions" above for full list of files in the CVDP dataset.
Please see LICENSE and NOTICE for licensing information. See CHANGELOG for changes.
This is the Comprehensive Verilog Design Problems (CVDP) benchmark dataset to use with the CVDP infrastructure on GitHub.