Back to Arena

Bisheng

by dataelement

System Card

Organizationdataelement
Released2023-08
Architectureagentic-workflow / Enterprise RAG/agent platform with HITL memory
DetailsEnterprise LLMOps platform blending workflows, RAG, multi-agent, and model management. Unique HITL workflow engine; five-year document-parsing training data; RBAC/SSO/LDAP.
Parameters—
Domainagent-memoryrag-retrieval
Open SourceYes
WebsiteVisit
CodeRepository
enterprisehitldoc-parsingrbac

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
78.980p
MemoryBank
no data
Cross-Session Memory
1/1
LongMemEval
79.475p
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
72.454p
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:Bisheng (dataelement/bisheng); evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)Bisheng (dataelement/bisheng); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)Bisheng (dataelement/bisheng); evaluated on AgentBench Memory Track (Tsinghua KEG, 2308)Bisheng (dataelement/bisheng); evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)Bisheng (dataelement/bisheng); evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)Bisheng (dataelement/bisheng); evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)