Back to Arena

LlamaCloud

by LlamaIndex Inc.

System Card

OrganizationLlamaIndex Inc.
Released2024-02
Architecturevector-rag / managed RAG infrastructure with LlamaParse
DetailsLlamaCloud is LlamaIndex's managed service offering, wrapping the open-source LlamaIndex framework in a hosted API. Core features include LlamaParse (proprietary document parser for complex PDFs/tables), managed vector indexes, and retrieval APIs with metadata filtering. Designed to operationalize RAG pipelines built with LlamaIndex without managing embedding and storage infrastructure.
Parameters—
Domainrag-retrieval
Open SourceNo
WebsiteVisit
LlamaIndexLlamaParsemanageddocument-parsingretrieval-API

Capability Profile

Benchmark Scores

5 of 14 benchmarks
Long-Context Retrieval
2/5
RULER
67.720p
NIAH
no data
LooGLE
no data
LongBench
603p
∞Bench
no data
Multi-Turn Recall
0/2
LoCoMo
no data
MemoryBank
no data
Cross-Session Memory
0/1
LongMemEval
no data
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
62.913p
HotpotQA
60.514p
Agent Task Memory
0/1
AgentBench-Mem
no data
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
1/1
RAGAS
63.77p
Sources:LlamaCloud vendor documentation; evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)LlamaCloud vendor documentation; evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)LlamaCloud vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)LlamaCloud vendor documentation; evaluated on RAGAS: Automated Evaluation of Retrieval-Augmented Generation (Exploding Gradients, 2309)LlamaCloud vendor documentation; evaluated on RULER: What's the Real Context Size of Your Long-Context Language Models (NVIDIA, 2404)