Back to Arena

R2R

by SciPhi-AI

System Card

OrganizationSciPhi-AI
Released2024-02
Architecturehybrid / Production RAG with auto-KG and deep-research agent
DetailsREST API + Python/TypeScript SDKs for multimodal document ingestion, hybrid semantic/keyword search, automatic knowledge-graph extraction, Deep Research multi-step reasoning agent, auth and RBAC.
Parameters—
Domainrag-retrievalknowledge-graph
Open SourceYes
WebsiteVisit
CodeRepository
deep-researchrbachybrid-searchsciphi

Capability Profile

Benchmark Scores

6 of 14 benchmarks
Long-Context Retrieval
2/5
RULER
73.368p
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
1/1
LongMemEval
72.430p
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
74.677p
HotpotQA
69.441p
Agent Task Memory
0/1
AgentBench-Mem
no data
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
1/1
RAGAS
71.769p
Sources:R2R (SciPhi-AI/R2R); evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)R2R (SciPhi-AI/R2R); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)R2R (SciPhi-AI/R2R); evaluated on RAGAS: Automated Evaluation of Retrieval-Augmented Generation (Exploding Gradients, 2309)R2R (SciPhi-AI/R2R); evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)R2R (SciPhi-AI/R2R); evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)R2R (SciPhi-AI/R2R); evaluated on RULER: What's the Real Context Size of Your Long-Context Language Models (NVIDIA, 2404)