Back to Arena

TrustRAG

by GoMate Community

System Card

OrganizationGoMate Community
Released2024-06
Architecturehybrid / Configurable modular RAG with deep-search
DetailsModular pipeline (parsing, retrieval, reranking, generation). BM25+dense hybrid; BGE/LLM pointwise/pairwise reranking; Milvus/Qdrant; web search; Deep Search / slow thinking / research reports.
Parameters—
Domainrag-retrieval
Open SourceYes
CodeRepository
modulardeep-searchrerankingresearch-report

Capability Profile

Benchmark Scores

5 of 14 benchmarks
Long-Context Retrieval
2/5
RULER
68.727p
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
0/1
LongMemEval
no data
Multi-Hop QA
2/3
BABILong
no data
MultiHop-RAG
7579p
HotpotQA
75.371p
Agent Task Memory
0/1
AgentBench-Mem
no data
Personalization
0/1
PerLTQA
no data
Factuality / Grounding
1/1
RAGAS
71.566p
Sources:TrustRAG (gomate-community/TrustRAG); evaluated on HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering (Stanford / CMU, 1809)TrustRAG (gomate-community/TrustRAG); evaluated on LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (Tsinghua KEG, 2308)TrustRAG (gomate-community/TrustRAG); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)TrustRAG (gomate-community/TrustRAG); evaluated on RAGAS: Automated Evaluation of Retrieval-Augmented Generation (Exploding Gradients, 2309)TrustRAG (gomate-community/TrustRAG); evaluated on RULER: What's the Real Context Size of Your Long-Context Language Models (NVIDIA, 2404)