Back to Arena

Astra DB

by DataStax

System Card

OrganizationDataStax
Released2020-01
Architecturevector-rag / managed Cassandra with vector search
DetailsAstra DB is DataStax's managed cloud database built on Apache Cassandra, extended with vector similarity search (ANN via JVector library) in August 2023. It combines Cassandra's partition-key scalability with vector indexing, enabling multi-tenant, high-throughput vector workloads with CQL queries. The Astra Streaming service adds real-time data ingestion via Pulsar.
Parameters—
Domainrag-retrieval
Open SourcePartial
WebsiteVisit
Cassandramanagedmulti-cloudANNstreaming

Capability Profile

Benchmark Scores

5 of 14 benchmarks
Long-Context Retrieval
2/5
RULER
67.117p
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
64.621p
HotpotQA
66.635p
Agent Task Memory
0/1
AgentBench-Mem
no data
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
1/1
RAGAS
63.64p
Sources:Astra DB vendor documentation; evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)Astra DB vendor documentation; evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)Astra DB vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)Astra DB vendor documentation; evaluated on RAGAS: Automated Evaluation of Retrieval-Augmented Generation (Exploding Gradients, 2309)Astra DB vendor documentation; evaluated on RULER: What's the Real Context Size of Your Long-Context Language Models (NVIDIA, 2404)