| #1 | QdrantQdrant | 75 | Qdrant (qdrant/qdrant); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #2 | AllegroGraphFranz Inc. | 75 | AllegroGraph vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #3 | AppAgentTencent / mnotgod96 | 75 | AppAgent paper (arXiv:2312.13771); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #4 | Athina AIAthina AI (YC W23) | 75 | Athina AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #5 | AutoWebGLMTHUDM | 75 | AutoWebGLM paper (arXiv:2404.03648); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #6 | Backboard IOBackboard.io | 75 | Backboard IO vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #7 | BotpressBotpress Inc. | 75 | Botpress vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #8 | BrowserGymServiceNow Research | 75 | BrowserGym paper (arXiv:2412.05467); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #9 | D-MemYou et al. (2025) | 75 | D-Mem paper (arXiv:2603.18631); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #10 | DB-GPTeosphoros-ai | 75 | DB-GPT (eosphoros-ai/DB-GPT); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #11 | DiffbotDiffbot Inc. | 75 | Diffbot vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #12 | DifyLangGenius | 75 | Dify (langgenius/dify); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #13 | GraphRAG-SDKFalkorDB | 75 | GraphRAG-SDK (FalkorDB/GraphRAG-SDK); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #14 | HiMemZhu et al. (JD.com, 2026) | 75 | HiMem paper (arXiv:2601.06377); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #15 | HippoRAGOSU NLP Group (Ohio State University) | 75 | HippoRAG paper (arXiv:2405.14831); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #16 | HippoRAG 2OSU NLP Group | 75 | HippoRAG 2 paper (arXiv:2502.14802); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #17 | HuggingGPT / JARVISMicrosoft Research | 75 | HuggingGPT / JARVIS paper (arXiv:2303.17580); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #18 | KnowAgentzjunlp (Zhejiang University) | 75 | KnowAgent paper (arXiv:2403.03101); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #19 | Lyzr CognisLyzr AI | 75 | Lyzr Cognis vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #20 | MCP Memory ServerAnthropic / Model Context Protocol | 75 | MCP Memory Server (modelcontextprotocol/servers); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #21 | MemR32025 (December submission) | 75 | MemR3 paper (arXiv:2512.20237); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #22 | MIRIXMIRIX AI (Wang, Chen) | 75 | MIRIX paper (arXiv:2507.07957); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #23 | MultiOnMultiOn (now AGI Inc.) | 75 | MultiOn vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #24 | Nano GraphRAGgusye1234 | 75 | Nano GraphRAG (gusye1234/nano-graphrag); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #25 | Ontotext GraphDBOntotext / Graphwise (merged with Semantic Web Company, 2025) | 75 | Ontotext GraphDB vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #26 | PathRAGBUPT-GAMMA | 75 | PathRAG paper (arXiv:2502.14902); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #27 | RMMGoogle / UCSB (2025) | 75 | RMM paper (arXiv:2503.08026); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #28 | StardogStardog Union Inc. | 75 | Stardog vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #29 | SuperAGITransformerOptimus | 75 | SuperAGI (TransformerOptimus/SuperAGI); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #30 | TrustRAGGoMate Community | 75 | TrustRAG (gomate-community/TrustRAG); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #31 | Vellum AIVellum AI Inc. (YC W23) | 75 | Vellum AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #32 | xmemoryxmemory Inc. | 75 | xmemory vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #33 | CradleBAAI-Agents | 74.7 | Cradle paper (arXiv:2403.03186); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #34 | HebbiaHebbia, Inc. | 74.6 | Hebbia vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #35 | R2RSciPhi-AI | 74.6 | R2R (SciPhi-AI/R2R); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #36 | LangGraphLangChain | 74.5 | LangGraph (langchain-ai/langgraph); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #37 | Onyxonyx-dot-app | 74.5 | Onyx (onyx-dot-app/onyx); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #38 | VoiceflowVoiceflow Inc. | 74.4 | Voiceflow vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #39 | AutoGen Core MemoryMicrosoft | 74.3 | AutoGen Core Memory paper (arXiv:2308.08155); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #40 | KAGOpenSPG / Ant Group | 74.3 | KAG paper (arXiv:2409.13731); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #41 | LagentInternLM (Shanghai AI Lab) | 74.3 | Lagent (InternLM/lagent); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #42 | CognigyCognigy GmbH (acquired by NICE, July 2025) | 74.2 | Cognigy vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #43 | Neo4j AuraDBNeo4j Inc. | 74.2 | Neo4j AuraDB vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #44 | Neo4j LLM Graph BuilderNeo4j Labs | 74.2 | Neo4j LLM Graph Builder (neo4j-labs/llm-graph-builder); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #45 | WebVoyagerMinorJerry et al. | 74.2 | WebVoyager paper (arXiv:2401.13919); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #46 | AutoGen StudioMicrosoft Research | 74.1 | AutoGen Studio vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #47 | VectorShiftVectorShift Inc. (YC S23) | 74.1 | VectorShift vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #48 | GraphRAGMicrosoft | 74 | GraphRAG paper (arXiv:2404.16130); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #49 | LangSmith LangGraph CloudLangChain Inc. | 73.9 | LangSmith LangGraph Cloud vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #50 | Self-RAGUniversity of Washington / Allen AI (Asai et al.) | 73.9 | Self-RAG paper (arXiv:2310.11511); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #51 | AutoGPT PlatformSignificant Gravitas | 73.7 | AutoGPT Platform (Significant-Gravitas/AutoGPT); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #52 | Galileo AIGalileo Technologies Inc. | 73.6 | Galileo AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #53 | RAGFlowInfiniFlow | 73.5 | RAGFlow (infiniflow/ragflow); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #54 | MemoryScopeAlibaba ModelScope | 73.2 | MemoryScope (modelscope/MemoryScope); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #55 | CrewAICrewAI Inc. (Joao Moura) | 73.2 | CrewAI (joaomdmoura/crewAI); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #56 | Swarmskyegomez / Swarms Corp | 73.2 | Swarms (kyegomez/swarms); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #57 | Maxim AIMaxim AI Inc. | 73.1 | Maxim AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #58 | Open InterpreterOpenInterpreter | 72.9 | Open Interpreter (OpenInterpreter/open-interpreter); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #59 | MilvusZilliz | 72.8 | Milvus (milvus-io/milvus); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #60 | AgentVerseOpenBMB (Tsinghua) | 72.8 | AgentVerse paper (arXiv:2308.10848); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #61 | Dust ttDust (formerly XP1) | 72.7 | Dust tt vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #62 | Lindy AILindy AI | 72.7 | Lindy AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #63 | ChatDBTsinghua University (Hu et al.) | 72.6 | ChatDB paper (arXiv:2306.03901); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #64 | AriGraphAIRI Institute / Moscow | 72.5 | AriGraph paper (arXiv:2407.04363); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #65 | Mixedbread AIMixedbread AI | 72.5 | Mixedbread AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #66 | PaperQA2FutureHouse | 72.5 | PaperQA2 paper (arXiv:2409.13740); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #67 | Bishengdataelement | 72.4 | Bisheng (dataelement/bisheng); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #68 | SID AISID (YC) | 72.4 | SID AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #69 | SupermemorySupermemory | 72.4 | Supermemory (supermemoryai/memorybench); evaluated on MultiHop-RAG (HKUST, 2024) |
| #70 | MoTFudan (Li, Qiu) | 72.3 | MoT paper (arXiv:2305.05181); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #71 | Haystack Memorydeepset | 72.1 | Haystack Memory (deepset-ai/haystack); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #72 | LangflowLangflow-ai (DataStax) | 72 | Langflow (langflow-ai/langflow); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #73 | NemoriNemori AI (independent) | 72 | Nemori paper (arXiv:2508.03341); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #74 | Qwen-AgentQwenLM (Alibaba) | 72 | Qwen-Agent (QwenLM/Qwen-Agent); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #75 | SynapseNTU / Salesforce (Zheng et al.) | 72 | Synapse paper (arXiv:2306.07863); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #76 | PineconePinecone Systems | 71.9 | Pinecone vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #77 | LightRAGHKUDS (HKU Data Intelligence Lab) | 71.9 | LightRAG paper (arXiv:2410.05779); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #78 | HoneyHiveHoneyHive Inc. | 71.7 | HoneyHive vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #79 | FlowiseFlowiseAI | 71.3 | Flowise (FlowiseAI/Flowise); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #80 | HybridAGISynaLinks | 71.3 | HybridAGI (SynaLinks/HybridAGI); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #81 | LarimarIBM Research | 71.3 | Larimar paper (arXiv:2403.11901); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #82 | MarkerDatalab (datalab-to) | 71.3 | Marker (datalab-to/marker); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #83 | CAMELCAMEL-AI.org | 71.1 | CAMEL paper (arXiv:2303.17760); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #84 | GleanGlean Technologies | 71.1 | Glean vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #85 | LangMemLangChain | 71 | LangMem (langchain-ai/langmem); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #86 | Cohere EmbedCohere Inc. | 70.9 | Cohere Embed vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #87 | Kore AIKore.ai Inc. | 70.8 | Kore AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #88 | WeaviateWeaviate | 70.7 | Weaviate (weaviate/weaviate); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #89 | ChatDev 2.0OpenBMB | 70.5 | ChatDev 2.0 paper (arXiv:2307.07924); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #90 | AGiXTJosh-XT | 70.4 | AGiXT (Josh-XT/AGiXT); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #91 | Think-in-MemoryAnt Group / Alibaba (Liu et al.) | 70.4 | Think-in-Memory paper (arXiv:2311.08719); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #92 | Memoripycaspianmoon | 70.3 | Memoripy (caspianmoon/memoripy); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #93 | SynapseNanyang Technological University (Zheng et al.) | 70.3 | Synapse paper (arXiv:2306.07863); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #94 | LlamaIndex MemoryLlamaIndex | 70.2 | LlamaIndex Memory (run-llama/llama_index); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #95 | MetaGPTDeepWisdom / geekan | 70.2 | MetaGPT paper (arXiv:2308.00352); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #96 | Stack AIStack AI Inc. (YC W23) | 70.2 | Stack AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #97 | GPTeam101dotxyz | 69.7 | GPTeam (101dotxyz/GPTeam); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #98 | Nomic AtlasNomic AI Inc. | 69.7 | Nomic Atlas vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #99 | Mobile-AgentAlibaba Tongyi Lab (X-PLUG) | 69.4 | Mobile-Agent paper (arXiv:2508.15144); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #100 | ChromaChroma | 69.2 | Chroma (chroma-core/chroma); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #101 | FastGPTlabring | 69.2 | FastGPT (labring/FastGPT); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #102 | SelfmemTsinghua / Microsoft (Cheng et al.) | 69 | Selfmem paper (arXiv:2305.02437); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #103 | Voyage AIVoyage AI (acquired by MongoDB, Feb 2025) | 69 | Voyage AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #104 | MiniRAGHKUDS | 68.4 | arXiv:2501.06713 Table 1 — Accuracy with gpt-4o-mini; SLM backbones: Phi-3.5-mini 49.96, GLM-Edge 51.41, Qwen2.5-3B 48.55 |
| #105 | MemoChatUniversity of Warwick / Alibaba | 67.9 | MemoChat paper (arXiv:2308.08239); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #106 | MemoriGibsonAI | 67.6 | Memori (GibsonAI/memori); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #107 | GraphitiZep AI | 66.4 | Zep / Graphiti paper |
| #108 | Mnemosyneindependent | 66.1 | Mnemosyne paper (arXiv:2510.08601); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #109 | ParadeDBParadeDB Inc. (YC S23) | 65.8 | ParadeDB vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #110 | REALMGoogle Research (Guu et al.) | 65.6 | REALM paper (arXiv:2002.08909); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #111 | Couchbase VectorCouchbase Inc. | 65.5 | Couchbase Vector vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #112 | txtaiNeuML | 65.4 | txtai (neuml/txtai); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #113 | Elasticsearch VectorElastic N.V. | 65.4 | Elasticsearch Vector vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #114 | PrivateGPTZylon AI | 65.3 | PrivateGPT (zylon-ai/private-gpt); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #115 | Mem AIMem Labs | 64.9 | Mem AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #116 | VectaraVectara Inc. | 64.9 | Vectara vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #117 | ZepZep AI | 64.8 | Zep evals |
| #118 | Astra DBDataStax | 64.6 | Astra DB vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #119 | Saner AISaner.AI | 64.6 | Saner AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #120 | MarqoMarqo Pty Ltd | 64.3 | Marqo vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #121 | MyScaleMyScale Inc. | 64.1 | MyScale vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #122 | ColPaliilluin-tech | 63.9 | ColPali paper (arXiv:2407.01449); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #123 | RETRODeepMind (Borgeaud et al.) | 63.8 | RETRO paper (arXiv:2112.04426); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #124 | MemoryBankHarbin Institute of Technology / SenseTime | 63.6 | MemoryBank paper (arXiv:2305.10250); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #125 | OpenSearch VectorOpenSearch Project (AWS-led) | 63.2 | OpenSearch Vector vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #126 | Neon VectorNeon Inc. | 63.1 | Neon Vector vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #127 | Redis VectorRedis Ltd. | 63 | Redis Vector vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #128 | AtlasMeta AI FAIR (Izacard et al.) | 62.9 | Atlas paper (arXiv:2208.03299); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #129 | Carbon AICarbon (acquired by Perplexity, Dec 2024) | 62.9 | Carbon AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #130 | CognitaTrueFoundry | 62.9 | Cognita (truefoundry/cognita); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #131 | LlamaCloudLlamaIndex Inc. | 62.9 | LlamaCloud vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #132 | Unstructured IOUnstructured Technologies Inc. | 62.8 | Unstructured IO vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #133 | MendableMendable (YC-backed) | 62.7 | Mendable vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #134 | Manticore SearchManticore Software Ltd. | 62.3 | Manticore Search vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #135 | VerbaWeaviate | 62.3 | Verba (weaviate/Verba); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #136 | EpsillaEpsilla Inc. (YC S23) | 61.6 | Epsilla vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #137 | RagieRagie Inc. | 61.5 | Ragie vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #138 | pgvector Supabase Neonpgvector OSS / Supabase Inc. / Neon Inc. | 61.3 | pgvector Supabase Neon vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #139 | TurboPufferTurboPuffer Inc. | 60.9 | TurboPuffer vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #140 | Supabase VectorSupabase Inc. | 60.8 | Supabase Vector vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #141 | Vespa AIYahoo / Vespa.ai (independent OSS project) | 60.5 | Vespa AI vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #142 | QuivrQuivrHQ | 60.4 | Quivr (QuivrHQ/quivr); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #143 | SingleStore VectorSingleStore Inc. | 60.4 | SingleStore Vector vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #144 | AnythingLLMMintplex Labs | 60.3 | AnythingLLM (Mintplex-Labs/anything-llm); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #145 | MongoDB Atlas VectorMongoDB Inc. | 60.1 | MongoDB Atlas Vector vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #146 | MemoroMIT Media Lab | 60 | Memoro paper (arXiv:2403.02135); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #147 | ValdYahoo Japan | 60 | Vald vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #148 | vectorizeVectorize Inc. | 59.3 | vectorize vendor documentation; evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401) |
| #149 | CogneeCognee | 57.2 | Cognee benchmark |
| #150 | MemaryKingjulio8238 | 52.7 | Memary repo evals |