Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
ParseBench
Datasets & benchmarksParseBench - A Document Parsing Benchmark for AI Agents
git clone https://github.com/run-llama/ParseBench.git -
documentation-images
Datasets & benchmarksHugging Face dataset by huggingface
huggingface/documentation-images -
cad-1000-hours
Datasets & benchmarksHugging Face dataset by markov-ai
markov-ai/cad-1000-hours -
MiMo-V2.6-RL-oss
Datasets & benchmarksHugging Face dataset by XiaomiMiMo
XiaomiMiMo/MiMo-V2.6-RL-oss -
GAIA
Datasets & benchmarksHugging Face dataset by gaia-benchmark
gaia-benchmark/GAIA -
olmOCR-bench
Datasets & benchmarksHugging Face dataset by allenai
allenai/olmOCR-bench -
ParseBench
Datasets & benchmarksHugging Face dataset by llamaindex
llamaindex/ParseBench -
developer-productivity-simulated-behavioral-data
Datasets & benchmarksHugging Face dataset by strova-ai
strova-ai/developer-productivity-simulated-behavioral-data -
ocr
Datasets & benchmarksHugging Face dataset by uv-scripts
uv-scripts/ocr -
arxiv-papers
Datasets & benchmarksHugging Face dataset by nick007x
nick007x/arxiv-papers -
humanities_data_benchmark
Datasets & benchmarksLLM Benchmark Suite for Humanities Data
git clone https://github.com/RISE-UNIBAS/humanities_data_benchmark.git -
ToolMind
Datasets & benchmarksHugging Face dataset by Nanbeige
Nanbeige/ToolMind -
DocLayNet
Datasets & benchmarksHugging Face dataset by docling-project
docling-project/DocLayNet -
apex-agents
Datasets & benchmarksHugging Face dataset by mercor
mercor/apex-agents -
product-database
Datasets & benchmarksHugging Face dataset by openfoodfacts
openfoodfacts/product-database -
Long-Horizon-Terminal-Bench
Datasets & benchmarksHugging Face dataset by IntelligenceLab
IntelligenceLab/Long-Horizon-Terminal-Bench -
arxiv_dataset
Datasets & benchmarksHugging Face dataset by arxiv-community
arxiv-community/arxiv_dataset -
confabulations
Datasets & benchmarksHallucinations (Confabulations) Document-Based Benchmark for RAG. Includes human-verified questions and answers.
git clone https://github.com/lechmazur/confabulations.git -
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
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.