Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
arxiv_dataset
Datasets & benchmarksHugging Face dataset by arxiv-community
arxiv-community/arxiv_dataset -
yambda
Datasets & benchmarksHugging Face dataset by yandex
yandex/yambda -
arxiv-complete
Datasets & benchmarksHugging Face dataset by secemp9
secemp9/arxiv-complete -
rag-dataset-12000
Datasets & benchmarksHugging Face dataset by neural-bridge
neural-bridge/rag-dataset-12000 -
lasagna
Datasets & benchmarksSwap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augmented Generation Compositionality": 450 configurations, eight benchmarks, corpora from 5K to 200K documents.
git clone https://github.com/dolev31/lasagna.git -
deepsearchqa
Datasets & benchmarksHugging Face dataset by google
google/deepsearchqa -
AmericanStories
Datasets & benchmarksHugging Face dataset by dell-research-harvard
dell-research-harvard/AmericanStories -
Recap-DataComp-1B
Datasets & benchmarksHugging Face dataset by UCSC-VLAA
UCSC-VLAA/Recap-DataComp-1B -
frames-benchmark
Datasets & benchmarksHugging Face dataset by google
google/frames-benchmark -
primitive-bench
Datasets & benchmarksThe marketplace for verifiable AI outcomes: state a task, get a fixed price upfront, and Primitive Bench routes across tools to complete it, refunded if the outcome isn't delivered. This repo is the open verification layer.
git clone https://github.com/primitive-bench/primitive-bench.git -
pii-masking-200k
Datasets & benchmarksHugging Face dataset by ai4privacy
ai4privacy/pii-masking-200k
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.