datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
mixlora-eval-data
🚀 MixLoRA Evaluation Data
This dataset is the held-out multimodal evaluation suite used in
Multimodal Instruction Tuning with Conditional Mixture of LoRA (ACL 2024).
It bundles 9 instruction-formatted tasks (mm_tasks/) plus the MME benchmark
(mme/) used to evaluate MixLoRA and baseline models in the paper.
The 9 tasks in mm_tasks/ are the zero-shot / held-out task split from
Vision-Flan. MME is a
separate benchmark, evaluated independently.
Dataset Structure… See the full description on the dataset page: https://huggingface.co/datasets/yingss/mixlora-eval-data.Egocentric_10K_Evaluation
Dataset Card for Egocentric_10K_Evaluation
This is a FiftyOne dataset with 30000 samples.
Installation
If you haven't already, install FiftyOne:
pip install -U fiftyone
Usage
import fiftyone as fo
from fiftyone.utils.huggingface import load_from_hub
# Load the dataset
# Note: other available arguments include 'max_samples', etc
dataset = load_from_hub("Voxel51/Egocentric_10K_Evaluation")
# Launch the App
session = fo.launch_app(dataset)
Dataset… See the full description on the dataset page: https://huggingface.co/datasets/Voxel51/Egocentric_10K_Evaluation.ops-eval
OPS-Eval: Leakage-Resistant Evaluation for Optical Pooled Screens
Benchmark artifacts for evaluating representation learning on pooled CRISPR
microscopy data. This dataset accompanies a submission to the NeurIPS 2026
Evaluations and Datasets Track.
Contents
Directory/File
Description
Size
montages/
Per-gene montage images (4 channels x 2 phases, ~10 PNGs per gene)
~66 GB
cell_embeddings/
Pre-extracted 512-dim cell embeddings per sgRNA (.npz)
~15 GB… See the full description on the dataset page: https://huggingface.co/datasets/cspeters119/ops-eval.WEIRD
WEIRD
Описание задачи
WEIRD – это расширенная версия подзадачи бинарной классификации оригинального английского бенчмарка WHOOPS!. Датасет оценивает, способна ли мультимодальная модель обнаруживать нарушения здравого смысла в изображениях. Здесь нарушение здравого смысла – это ситуации, противоречащие типичным нормам реальности. Например, пингвины не могут летать, дети не водят автомобили, посетители не накладывают еду официантам, и так далее. В датасете поровну… See the full description on the dataset page: https://huggingface.co/datasets/MERA-evaluation/WEIRD.CLIP-FMoE-Evaluation
CLIP-FMoE Evaluation Data
Evaluation datasets used by the CLIP-FMoE repository.
Large raw image directories are stored as uncompressed .tar files. This avoids uploading millions of individual image files and makes download/extraction substantially faster.
Repository layout
clip_benchmark/wds_<dataset>/ Existing CLIP_benchmark WebDataset shards
retrieval/docci_iiw/ Metadata + docci_arr_new/images_aar.tar
retrieval/dci/ Annotations +… See the full description on the dataset page: https://huggingface.co/datasets/moneyzz432/CLIP-FMoE-Evaluation.nanopath-evals
NanoPath evaluation data
This is the immutable data mirror used by NanoPath probe protocol v2. It contains only the exact development records consumed by medarc/nanopath: selected THUNDER training/validation images, prepared development-only slide caches, and the two PathoROB subsets. manifest.json records SHA-256 checksums and binds the snapshot to the checked-in benchmark manifests.
No official THUNDER, HEST, or CPTAC classification test record is included. HEST is absent.… See the full description on the dataset page: https://huggingface.co/datasets/medarc/nanopath-evals.ppe-benchmark-eval
PPE Benchmark Eval Set (v1)
A held-out, human-verified benchmark for evaluating vision-language models on
personal protective equipment (PPE) detection — specifically hardhat and
safety-vest presence — framed as a VQA-style classification task.
What this is
96 images, balanced 24/24/24/24 across the four hardhat × vest combinations
(yes/yes, yes/no, no/yes, no/no). Sourced from a forked, filtered subset of
the karabuk-university PPE dataset
on Roboflow Universe… See the full description on the dataset page: https://huggingface.co/datasets/khadijah00/ppe-benchmark-eval.tiktok-techjam-2026-eval
TikTok TechJam 2026 Eval
Held-out demonstration pair used by Seer:
COCO val2017 photographs plus the WildFake DALL·E Advanced (DALL·E 3) subset.
Do not train on this split.
Contents
label
meaning
count
origin
0 / real
photograph
5,000
COCO val2017
1 / fake
AI-generated
8,843
WildFake DALL·E Advanced
Columns: image, label, source, generator, id.
id is the COCO stem for reals, and {session}_{stem} for fakes so duplicate
WildFake basenames stay… See the full description on the dataset page: https://huggingface.co/datasets/glennwuwu/tiktok-techjam-2026-eval.oven-qwen3-vl-eval-traces
OVEN Qwen3-VL Evaluation Traces
Raw evaluation traces from my MSc thesis: Qwen3-VL (2B / 4B / 8B / 32B) sampled
on the OVEN open-domain visual entity recognition task (aligned validation split),
with LM-as-judge verdicts. These are the rollouts behind the thesis's coverage
(pass@k) and specificity results.
Files are grouped by model size (2b/, 4b/, 8b/, 32b/):
file
contents
samples.jsonl
standard sampling: N=256 stochastic rollouts per example, under all_texts… See the full description on the dataset page: https://huggingface.co/datasets/jucamohedano/oven-qwen3-vl-eval-traces.japanese-image-classification-evaluation-dataset
recruit-jp/japanese-image-classification-evaluation-dataset
Overview
Developed by: Recruit Co., Ltd.
Dataset type: Image Classification
Language(s): Japanese
LICENSE: CC-BY-4.0
More details are described in our tech blog post.
日本語CLIP学習済みモデルとその評価用データセットの公開
Dataset Details
This dataset is comprised of four image classification tasks related to concepts and things unique to Japan. Specifically, is consists of the following tasks.
jafood101: Image… See the full description on the dataset page: https://huggingface.co/datasets/recruit-jp/japanese-image-classification-evaluation-dataset.evaluation-dataset
DeepSafe Evaluation Dataset
Evaluation set for DeepSafe,
a deepfake detection benchmark.
Tiers
Tier
Samples
Generators
Size
Use
master_eval_small/
198
116
1.7 GB
smoke test, under 2 min
master_eval/
15,454
411
10 GB
the standard benchmark
master_eval_full/
45,954
411
25 GB
complete set
Medium tier composition: 9,954 image, 3,500 audio, 2,000 video.
from huggingface_hub import snapshot_download
snapshot_download("deepsafe/evaluation-dataset"… See the full description on the dataset page: https://huggingface.co/datasets/deepsafe/evaluation-dataset.trace-rx-eval-predictions
TRACE-RX Evaluation Predictions
Per-image detector scores from an independent evaluation of the two TechJam 2026 TRACE-RX
detectors, run 30 Aug – 1 Sep 2026.
No images here. Every file contains scores, labels, asset ids and transform names only — this is
derived evaluation metadata, not a redistribution of any source imagery. The underlying corpora
(Joshyxwa/data_draft, Joshyxwa/techjam2026, techjam-aigc/wildfake-eval-subset) keep their own
terms, and data_draft's WildFake rows… See the full description on the dataset page: https://huggingface.co/datasets/joelleoqiyi/trace-rx-eval-predictions.Crop-Disease-Image-Eval-Synthetic
Crop, Category, Disease and Pest Test Set
11,057 smallholder-farmer photographs sent to FarmerChat from Ethiopia, India, Kenya and Nigeria, each
labelled with the crop, whether the problem is a disease or a pest, and which one. This is the held-out
test split of a four-head classification benchmark, restricted to the rows whose labels came from an
independent model council rather than from the production vendor.
Why 11,057 and not 16,275
The full held-out split is… See the full description on the dataset page: https://huggingface.co/datasets/DigiGreen/Crop-Disease-Image-Eval-Synthetic.lipika-eval
Lipika eval — Indic font recognition benchmark
The frozen validation set behind loopdesk-ai/lipika
(Indic font recognizer): 6,876 synthetic text crops covering 553 freely-licensed font
families across 13 scripts (Devanagari, Bengali, Gujarati, Gurmukhi, Kannada, Malayalam,
Meetei Mayek, Odia, Ol Chiki, Perso-Arabic, Tamil, Telugu, Latin).
This is the set reported as "synthetic val" in the model card (Lipika v2.4 scores 0.849
family top-1 / 0.977 top-5 / 0.991 script). Use it to… See the full description on the dataset page: https://huggingface.co/datasets/loopdesk-ai/lipika-eval.MUMU-Eval-6000
MUMU Eval 6000
This repository contains the 6,000-image source-data evaluation set used for
the Florence-2 and LFM2.5-VL-450M baselines in the MUMU evaluation repository.
It is an independently prepared research split, not an official MUMU Challenge
release.
Splits
Split
Images
Ground truth in manifest
validation
1,000
Yes
test
5,000
Yes
The split contains 2,001 Task A samples, 2,000 Task B samples, and 1,999 Task C
samples. All 6,000 image… See the full description on the dataset page: https://huggingface.co/datasets/JinyuLiu/MUMU-Eval-6000.mlcd-mteb-cifar-eval
MLCD vs CLIP on MTEB CIFAR-10/100: integration and evaluation
Evaluation results accompanying the MTEB integration of two MLCD image encoders
(PR #5406, resolving
issue #2571).
Two DeepGlint-AI MLCD encoders were integrated into MTEB, verified against the
reference implementation, and evaluated on the official MTEB CIFAR-10/CIFAR-100
image-classification tasks alongside size-matched OpenAI CLIP baselines.
What was measured
Official MTEB image classification: 5… See the full description on the dataset page: https://huggingface.co/datasets/b4ph/mlcd-mteb-cifar-eval.solring-eval
Sol Ring Dataset
(c) 2026, HanClinto Games, LLC
A collection of 307 reference frames for benchmarking Magic: The Gathering card
identification — specifically edition (set) discrimination under real-world
camera conditions.
Purpose
To provide a meaningful, reproducible metric for measuring and comparing the
accuracy of card recognition algorithms, with particular focus on
set / edition identification rather than just card-name recognition.
Theory
In Magic: The… See the full description on the dataset page: https://huggingface.co/datasets/HanClinto/solring-eval.wonders-of-world-images-hf
🌍 Wonders of the World Images 🏛️
¡Bienvenido/a a un viaje visual por las maravillas del mundo!
Este dataset contiene imágenes de 12 maravillas icónicas, listas para que entrenes modelos de visión por computadora, juegues a ser explorador o simplemente disfrutes de la diversidad arquitectónica y natural del planeta.
📦 Estructura del dataset
Clases:
Burj Khalifa
Chichen Itza
Christ the Redeemer
Eiffel Tower
Great Wall of China
Machu Picchu
Pyramids of Giza
Roman… See the full description on the dataset page: https://huggingface.co/datasets/evalverden/wonders-of-world-images-hf.spherical-equivariance-bench
Spherical Equivariance Benchmark: Classical Spectral Convolution vs SoLA
A reusable benchmark that turns the accidental link mismatch between two different
SO(3)-equivariant-on-the-sphere works into a head-to-head comparison under one common
rotation-equivariance test harness:
Classical spectral spherical convolution — Cohen, Geiger, Köhler & Welling,
Learning SO(3)-Equivariant Representations with Spherical CNNs, ICML 2018
(arXiv:1711.06721). Implemented here as a
zonal… See the full description on the dataset page: https://huggingface.co/datasets/evalstate/spherical-equivariance-bench.piyoshogi-eval
PiyoShogi Eval (paired, 4 devices)
ぴよ将棋の盤面認識モデルの評価用データセット。4機種の実機スクリーンショットを SFEN 単位で束ねた横持ち形式。
対応機種
機種名
識別子 (devices 列)
画面解像度
iPhone 8
iPhone10,1
750 × 1334
iPhone XR
iPhone11,8
828 × 1792
iPhone 15
iPhone15,4
1179 × 2556
iPad Air M3
iPad14,10
1640 × 2360
paired config
1 行 = 1 SFEN、4 機種分の画像を list で持つ。
Column
Type
説明
sfen
string
SFEN形式の局面文字列
hash
string
SFENのSHA-256
type
string
局面ソース種別（現状は全て existing = ぴよ将棋プリセット由来）… See the full description on the dataset page: https://huggingface.co/datasets/ultemica/piyoshogi-eval.facepass_eval
FacePass Evaluation Dataset (Real LFW Faces)
This dataset contains real face images from the LFW (Labeled Faces in the Wild) dataset, curated for face recognition evaluation.
⚠️ IMPORTANT: This is the corrected version with actual face photographs (not colored squares).
Key Features
✅ Real faces: Actual photographs of people, not synthetic images✅ Balanced dataset: All individuals have 20+ images✅ Proper splits: 80/20 train/test split per person✅ Standardized: Resized to… See the full description on the dataset page: https://huggingface.co/datasets/besartshyti/facepass_eval.oceanguard-marine-debris-eval-1000
OceanGuard AI — Marine Debris Evaluation Hold-out (annotations only)
The held-out evaluation split used to report the LoRA adapter delta in the
OceanGuard AI Kaggle Gemma 4 Good Hackathon submission
(Global Resilience track + Unsloth bonus track).
Important — this repository contains only the annotations and metadata.
The 1 000 underwater / coastal images are not redistributed here. They
come from three pre-existing third-party datasets, each with its own
license. Reviewers and… See the full description on the dataset page: https://huggingface.co/datasets/asferrer/oceanguard-marine-debris-eval-1000.evals-eastrus-vl
evals-eastrus-vl
Independent evaluation dataset for the EstrusVision cattle estrus detection model. Contains ground-truth labels for measuring deployment readiness.
Contents
43 total samples (40 in-domain cattle vulval images, 3 out-of-domain)
Embedded image column (no external file dependencies)
Six symptom ground-truth labels per in-domain sample
out_of_domain flag for rejection testing
notes field with clinical observations
Label distribution (in-domain only)… See the full description on the dataset page: https://huggingface.co/datasets/prapaa/evals-eastrus-vl.chest-xrays-evaluation_cnn-cls
🩻 Chest X-Ray: Detección de Anomalías
Dataset de imágenes de radiografías de tórax procesadas para tareas de clasificación binaria (Normal vs Anomalía). Este dataset forma parte del curso de Deep Learning de inGeniia, utilizado para enseñar Redes Convolucionales (CNN) y Transfer Learning con modelos como YOLO11 (modo clasificación).
🖼️ Descripción del Dataset
Las imágenes han sido extraídas originalmente de Kaggle y procesadas con técnicas de Data Augmentation para… See the full description on the dataset page: https://huggingface.co/datasets/inGeniia/chest-xrays-evaluation_cnn-cls.sailor-moon-redraw-evalchest-xrays-evaluation_cnn-cls
🩻 Chest X-Ray: Detección de Anomalías
Dataset de imágenes de radiografías de tórax procesadas para tareas de clasificación binaria (Normal vs Anomalía). Este dataset forma parte del curso de Deep Learning de inGeniia, utilizado para enseñar Redes Convolucionales (CNN) y Transfer Learning con modelos como YOLO11 (modo clasificación).
🖼️ Descripción del Dataset
Las imágenes han sido extraídas originalmente de Kaggle y procesadas con técnicas de Data Augmentation para… See the full description on the dataset page: https://huggingface.co/datasets/edgardoporto/chest-xrays-evaluation_cnn-cls.evaluation
Skill-Aligned Annotation for Text-to-Image Evaluation
Companion dataset for the NeurIPS 2026 paper "Towards Objective Evaluation".
The dataset contains generated images from 7 text-to-image models, evaluated
by 6 human annotators (anonymized) plus an LLM judge across 9 skill-aligned
annotation strategies.
Configs
Config
Rows
Description
images
621
Generated images (621 WebP) with embedded bytes; one row per (prompt_id, generator).
prompts
179
Per-prompt… See the full description on the dataset page: https://huggingface.co/datasets/Skill-Aigned/evaluation.