Back to Arena

Pinecone

by Pinecone Systems

System Card

OrganizationPinecone Systems
Released2021-01
Architecturevector-rag / Managed serverless vector DB
DetailsFully managed vector database with serverless and pod-based deployment modes. Supports hybrid sparse-dense search, namespaces, metadata filtering, and per-region replicas.
Parameters—
Domainrag-retrieval
Open SourceNo
WebsiteVisit
vector-dbmanagedserverlessproduction

Capability Profile

Benchmark Scores

5 of 14 benchmarks
Long-Context Retrieval
2/5
RULER
82.597p
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
71.949p
HotpotQA
52.44p
Agent Task Memory
0/1
AgentBench-Mem
no data
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
1/1
RAGAS
74.290p
Sources:Pinecone benchmarksPinecone evalsPinecone vendor documentation; evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)Pinecone vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)Pinecone vendor documentation; evaluated on RULER: What's the Real Context Size of Your Long-Context Language Models (NVIDIA, 2404)