Back to Arena

SingleStore Vector

by SingleStore Inc.

System Card

OrganizationSingleStore Inc.
Released2017-01
Architecturevector-rag / htap-native-vector
DetailsSingleStore has supported vector columns and similarity search since 2017, making it one of the earliest relational platforms with this capability. Its HTAP (hybrid transactional-analytical) engine handles vector search, full-text, SQL aggregations, and streaming ingestion in a single unified compute layer. Added additional vector index types and ANN optimizations in 2024.
Parameters—
Domainrag-retrieval
Open SourceNo
WebsiteVisit
htapsqlreal-timetransactionalearliest-vector-support

Capability Profile

Benchmark Scores

5 of 14 benchmarks
Long-Context Retrieval
2/5
RULER
7149p
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
60.45p
HotpotQA
61.918p
Agent Task Memory
0/1
AgentBench-Mem
no data
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
1/1
RAGAS
64.315p
Sources:SingleStore Vector vendor documentation; evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)SingleStore Vector vendor documentation; evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)SingleStore Vector vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)SingleStore Vector vendor documentation; evaluated on RAGAS: Automated Evaluation of Retrieval-Augmented Generation (Exploding Gradients, 2309)SingleStore Vector vendor documentation; evaluated on RULER: What's the Real Context Size of Your Long-Context Language Models (NVIDIA, 2404)