Back to Arena

Flowise

by FlowiseAI

System Card

OrganizationFlowiseAI
Released2023-04
Architectureagentic-workflow / Low-code agent + memory builder
DetailsDrag-and-drop flow builder (Node/React). Memory nodes (conversation buffer, window, summary, vector-store) plug into chains; supports RAG, multi-agent and LangChain integrations.
Parameters—
Domainagent-memoryrag-retrieval
Open SourceYes
WebsiteVisit
CodeRepository
low-codedrag-dropmulti-agentlangchain

Capability Profile

Benchmark Scores

6 of 14 benchmarks
Long-Context Retrieval
1/5
RULER
no data
NIAH
no data
LooGLE
no data
LongBench
603p
∞Bench
no data
Multi-Turn Recall
1/2
LoCoMo
73.939p
MemoryBank
no data
Cross-Session Memory
1/1
LongMemEval
75.349p
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
71.345p
HotpotQA
72.355p
Agent Task Memory
1/1
AgentBench-Mem
7226p
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
0/1
RAGAS
no data
Sources:Flowise (FlowiseAI/Flowise); evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)Flowise (FlowiseAI/Flowise); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)Flowise (FlowiseAI/Flowise); evaluated on AgentBench Memory Track (Tsinghua KEG, 2308)Flowise (FlowiseAI/Flowise); evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)Flowise (FlowiseAI/Flowise); evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)Flowise (FlowiseAI/Flowise); evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)