Back to Arena

Weaviate

by Weaviate

System Card

OrganizationWeaviate
Released2019-09
Architecturevector-rag / Open-source hybrid vector DB
DetailsOpen-source vector database with built-in modules for hybrid sparse-dense retrieval, generative search, and multi-tenant collections. Schema-aware with strong filtering support.
Parameters—
Domainrag-retrievalknowledge-graph
Open SourceYes
WebsiteVisit
CodeRepository
vector-dbhybrid-searchopen-sourceschema

Capability Profile

Benchmark Scores

6 of 14 benchmarks
Long-Context Retrieval
2/5
RULER
81.596p
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
1/1
LongMemEval
63.117p
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
70.741p
HotpotQA
53.15p
Agent Task Memory
0/1
AgentBench-Mem
no data
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
1/1
RAGAS
7379p
Sources:Weaviate benchmarksWeaviate evalsWeaviate (weaviate/weaviate); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)Weaviate (weaviate/weaviate); evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)Weaviate (weaviate/weaviate); evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)Weaviate (weaviate/weaviate); evaluated on RULER: What's the Real Context Size of Your Long-Context Language Models (NVIDIA, 2404)