datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
bankertoolbench
BankerToolBench
BankerToolBench is a benchmark of 100 end-to-end investment banking tasks for
evaluating AI agents. Each task mirrors real junior-banker work — building
financial models, preparing pitch decks, writing memos — and produces multi-file
deliverables (Excel, PowerPoint, Word) that are scored against expert-authored
rubrics.
The benchmark was developed with 502 investment bankers from firms including
Goldman Sachs, JPMorgan, Evercore, and others. Human completion time… See the full description on the dataset page: https://huggingface.co/datasets/lucids112/bankertoolbench.LUCid
📦 LUCid: Latent User Context Benchmark
Benchmarking situational relevance in lifelong personalization
📌 Dataset Summary
LUCid (Latent User Context) is a diagnostic dataset for evaluating situational relevance in lifelong personalization.
Grounded in Information Retrieval theory, LUCid is motivated by the observation that the information needed to personalize a response is often not the information that is most semantically similar to the user's query.… See the full description on the dataset page: https://huggingface.co/datasets/MichiganNLP/LUCid.LUCID-Socratic-10K
🧠 LUCID-Socratic-10K
The First Open Dataset for Socratic AI Tutoring
Aligned with the French National Curriculum
A high-quality synthetic dataset of 1,000+ multi-turn Socratic dialogues, adaptive quizzes, flashcards, and revision materials across 18 subjects and 7 grade levels — purpose-built for training pedagogically-aligned AI tutors.
📊 Explore the Data · 🚀 Quick Start · 📖 Paper · 🏗️ Architecture
🎯 What Makes… See the full description on the dataset page: https://huggingface.co/datasets/clemNova/LUCID-Socratic-10K.LUCid
📦 LUCid: Latent User Context Benchmark
Benchmarking situational relevance in lifelong personalization
📌 Dataset Summary
LUCid (Latent User Context) is a diagnostic dataset for evaluating situational relevance in lifelong personalization.
Grounded in Information Retrieval theory, LUCid is motivated by the observation that the information needed to personalize a response is often not the information that is most semantically similar to the user's query. Instead… See the full description on the dataset page: https://huggingface.co/datasets/anonymous-654/LUCid.