Back to Arena

Kore AI

by Kore.ai Inc.

System Card

OrganizationKore.ai Inc.
Released2014-01
Architectureagentic-workflow / enterprise agentic AI platform with multi-LLM
DetailsKore.ai provides an enterprise agentic AI platform for building both task-based and generative AI agents across CX and EX use cases. Supports a library of pre-built industry-specific agent templates, multi-LLM orchestration (swap models per node), and a RAG-based knowledge module. Includes XO Platform (bot builder), GALE (agent evaluation), and AgentAssist (live agent support).
Parameters—
Domainagent-memorypersonalization
Open SourceNo
WebsiteVisit
enterprisemulti-LLMindustry-templatesagenticcontact-center

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
75.552p
MemoryBank
76.857p
Cross-Session Memory
1/1
LongMemEval
79.778p
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
70.842p
HotpotQA
7362p
Agent Task Memory
1/1
AgentBench-Mem
7226p
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
0/1
RAGAS
no data
Sources:Kore AI vendor documentation; evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)Kore AI vendor documentation; evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)Kore AI vendor documentation; evaluated on AgentBench Memory Track (Tsinghua KEG, 2308)Kore AI vendor documentation; evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)Kore AI vendor documentation; evaluated on MemoryBank: Enhancing LLMs with Long-Term Memory (Sun Yat-sen University, 2305)Kore AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)