Back to Arena
Suki AI
by Suki (formerly Robin AI)
System Card
OrganizationSuki (formerly Robin AI)
Released2017-01
Architectureagentic-workflow / Voice-Enabled Clinical NLP Assistant
DetailsSuki uses voice-enabled NLP and machine learning to understand and execute doctors' verbal commands for note generation, EHR data retrieval, and coding workflows. It integrates natively with Epic AppOrchard, Cerner, and athenahealth. The architecture combines ASR with clinical domain-fine-tuned language models that understand medical terminology, specialty-specific documentation templates, and coding ontologies. Supports ambient documentation, dictation, and real-time coding across 130+ health systems.
Parameters—
Domainepisodic-session
Open SourceNo
WebsiteVisit
healthcarevoice-assistantehr-integrationclinical-codingambient-scribenlp
Capability Profile
Benchmark Scores
4 of 14 benchmarksLong-Context Retrieval0/5
RULER
no dataNIAH
no dataLooGLE
no dataLongBench
no data∞Bench
no dataMulti-Turn Recall2/2
Cross-Session Memory1/1
Multi-Hop QA0/3
BABILong
no dataMultiHop-RAG
no dataHotpotQA
no dataAgent Task Memory1/1
Personalization0/1
PerLTQA
no dataFactuality / Grounding0/1
RAGAS
no dataSources:Suki AI vendor documentation; evaluated on AgentBench Memory Track (Tsinghua KEG, 2308)Suki AI vendor documentation; evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)Suki AI vendor documentation; evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)Suki AI vendor documentation; evaluated on MemoryBank: Enhancing LLMs with Long-Term Memory (Sun Yat-sen University, 2305)