RAGBench

  Dataset Overview

RAGBEnch is a large-scale RAG benchmark dataset of 100k RAG examples. It covers five unique industry-specific domains and various RAG task types. RAGBench examples are sourced from industry corpora such as user manuals, making it particularly relevant for industry applications. RAGBench comrises 12 sub-component datasets, each one split into train/validation/test splits

  Usage

from datasets import load_dataset

load… See the full description on the dataset page: https://huggingface.co/datasets/galileo-ai/ragbench.

param-bharat/ragbench-dual-clf-preprocessed dataset hosted on Hugging Face and contributed by the HF Datasets community

MBPP dataset annotated with ground-truth programming solutions, to enable evaluations for retrieval and retrieval-augmented code generation. Please refer to code-rag-bench for more details.

The StackOverflow posts retrieval source for code-rag-bench.

DS-1000 dataset annotated with the ground-truth library documentation, to enable evaluations for retrieval and retrieval-augmented code generation. Please refer to [code-rag-bench] for more details

ODEX dataset annotated with the ground-truth library documentation, to enable evaluations for retrieval and retrieval-augmented code generation. Please refer to [code-rag-bench] for more details.

The entire dump of GitHub repositories.

Public RAG bench dataset with texts

Dataset Summary

This dataset is a domain-specific benchmark for Question Answering, using the Jeep 2023 Gladiator Car manual as its knowledge base. It combines the corpus from the original DelucionQA project by Bosch Research with questions sourced from the RAGBench dataset. The result is a challenging dataset designed to evaluate a system's ability to answer specific, technical questions based on a complex, real-world document.

  Supported Tasks

Question Answering:… See the full description on the dataset page: https://huggingface.co/datasets/corvicai/delucionqa.

code-rag-bench/code-retrieval-stackoverflow-small dataset hosted on Hugging Face and contributed by the HF Datasets community

REAL-MM-RAG-Bench: A Real-World Multi-Modal Retrieval Benchmark

We introduced REAL-MM-RAG-Bench, a real-world multi-modal retrieval benchmark designed to evaluate retrieval models in reliable, challenging, and realistic settings. The benchmark was constructed using an automated pipeline, where queries were generated by a vision-language model (VLM), filtered by a large language model (LLM), and rephrased by an LLM to ensure high-quality retrieval evaluation. To simulate real-world… See the full description on the dataset page: https://huggingface.co/datasets/ibm-research/REAL-MM-RAG_FinReport.

DRAGON bench history public texts. Date: 2025.07.10

RAG bench private QA dataset. Test version

DRAGON bench history private QA dataset. Date: 2025.07.10

DRAGON bench history public questions. Date: 2025.07.10

DRAGON bench history private texts (mappings). Date: 2025.07.10

ChatRAG Bench

ChatRAG Bench is a benchmark for evaluating a model's conversational QA capability over documents or retrieved context. ChatRAG Bench are built on and derived from 10 existing datasets: Doc2Dial, QuAC, QReCC, TopioCQA, INSCIT, CoQA, HybriDialogue, DoQA, SQA, ConvFinQA. ChatRAG Bench covers a wide range of documents and question types, which require models to generate responses from long context, comprehend and reason over tables, conduct arithmetic calculations, and… See the full description on the dataset page: https://huggingface.co/datasets/nvidia/ChatRAG-Bench.