Back to Arena

Voiceflow

by Voiceflow Inc.

System Card

OrganizationVoiceflow Inc.
Released2019-03
Architectureagentic-workflow / visual conversational agent builder
DetailsVoiceflow is a visual canvas platform for designing, prototyping, and deploying conversational AI agents (chat and voice). It supports knowledge base integration (RAG), variable memory for session context, multi-channel deployment (web, Alexa, Google Assistant), and team collaboration. Recently expanded to support multi-turn agentic workflows and LLM-powered intent recognition.
Parameters—
Domainagent-memoryepisodic-session
Open SourceNo
WebsiteVisit
conversational-AIvisual-canvasvoicechatbotmulti-channel

Capability Profile

Benchmark Scores

6 of 14 benchmarks
Long-Context Retrieval
0/5
RULER
no data
NIAH
no data
LooGLE
no data
LongBench
no data
∞Bench
no data
Multi-Turn Recall
2/2
LoCoMo
78.276p
MemoryBank
73.130p
Cross-Session Memory
1/1
LongMemEval
79.879p
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
74.475p
HotpotQA
74.969p
Agent Task Memory
1/1
AgentBench-Mem
7226p
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
0/1
RAGAS
no data
Sources:Voiceflow vendor documentation; evaluated on AgentBench Memory Track (Tsinghua KEG, 2308)Voiceflow vendor documentation; evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)Voiceflow vendor documentation; evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)Voiceflow vendor documentation; evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)Voiceflow vendor documentation; evaluated on MemoryBank: Enhancing LLMs with Long-Term Memory (Sun Yat-sen University, 2305)Voiceflow vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)