datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
memdoc
memdoc
A dataset for evaluating QA agents that retrieve from both conversational memory and a document corpus, while controlling for variance that comes from the question and its evidence themselves.
Each item is a question with 2-4 gold-evidence chunks partitioned across the two stores. The same questions and evidence can be presented as memory-only, document-only, or split across both. Because the question text and the underlying facts stay fixed, differences in agent… See the full description on the dataset page: https://huggingface.co/datasets/todor-cmd/memdoc.Structured-Todo-Lists-for-Learning-and-Projects
Academic Task Management Dataset
Overview
100 structured todo lists for academic and personal organization. Culturally diverse with 70% Indian education context, 25% European scenarios, and 5% other Asian contexts.
Dataset Structure
{
"input": "Task description",
"output": {
"type": "todo",
"title": "List title",
"category": "academic/personal/project",
"items": [
{"task": "...", "done": false, "priority": "low/medium/high"}
]
}… See the full description on the dataset page: https://huggingface.co/datasets/Srinivasmec26/Structured-Todo-Lists-for-Learning-and-Projects.shigyobench
ShigyoBench: 日本の士業資格試験ベンチマーク
日本の国家資格試験（士業）の過去問題を収録したLLM評価用ベンチマークデータセットです。
概要
項目
値
総問題数
8,979問
年度範囲
1988-2025
試験種別
8種類
形式
多肢選択式
収録試験
試験名
exam_type
問題数
subject
宅地建物取引士試験
takken
1,950
-
公認会計士試験
cpa
1,764
企業法, 管理会計論, 監査論, 財務会計論
司法試験予備試験
shihou_yobi
1,425
民法商法民事訴訟法, 憲法行政法, 刑法刑事訴訟法
司法試験
shihou
1,536
民法, 刑法, 憲法
弁理士試験
benrishi
1,200
-
不動産鑑定士試験
fudosan_kanteishi
400
-
司法書士試験
shihoshoshi
392
-
行政書士試験
gyoseishoshi
313
-… See the full description on the dataset page: https://huggingface.co/datasets/todo1111/shigyobench.