{"id":"niah-needle-in-a-haystack--gh-gkamradt-llmtest-needleinahaystack","name":"NIAH (Needle in a Haystack)","url":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/niah-needle-in-a-haystack--gh-gkamradt-llmtest-needleinahaystack","family":"memory-research","section":"Memory benchmarks & evaluation","sections":["Memory benchmarks & evaluation"],"tier":4,"last_verified_at":"2026-05-14","lifecycle":{"status":"active","severity":0,"note":null},"taxonomy":{"storage":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"retrieval":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"persistence":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"update":[{"value":"read-only","primary":true,"reason":null}],"unit":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"governance":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"conflict":[{"value":"n/a","primary":true,"reason":"not applicable (evaluation benchmark)"}]},"cells":{"type":{"value":"Single-fact verbatim retrieval from long context","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"desc":{"value":"Places a known sentence (\"needle\") at varying positions inside a long irrelevant document (\"haystack\") and prompts the model to retrieve it. Tests context lengths from 2K to model max. Greg Kamradt, 2023, no formal venue.","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"claims":{"value":"De facto first-pass filter for long-context LLM releases. Now considered necessary-but-insufficient — most frontier models score near-perfect.","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"modalities":{"value":"text","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"created":{"value":"2023-11","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","last_verified_at":"2026-05-12","source_class":"repo"},"latest-release":{"value":"no releases","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack/releases","status":"depth-floor-reached","tier":"T1","last_verified_at":"2026-05-12","source_class":"repo"},"license":{"value":"MIT","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack/blob/main/LICENSE","status":"real-data","tier":"T1","source_class":"repo"},"gh":{"value":"2.3k★ Jupyter Notebook","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","last_verified_at":"2026-05-12","source_class":"repo"},"mindshare":{"value":"no academic citations (informal GitHub project); de-facto first-pass filter for all frontier LLM releases","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","last_verified_at":"2026-05-12","source_class":"repo"},"citations":{"value":"not applicable — not academic","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-12"},"funding":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-06"},"customers":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"pricing":{"value":"not applicable — open source; free to use","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"compliance":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"data-handling":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"deployment":{"value":"not applicable — run locally","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"hq":{"value":"not applicable — not a company","citation":null,"status":"not-applicable","tier":"T3"},"founders":{"value":"Greg Kamradt (independent AI researcher); open-source 2023","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"volume":{"value":"not applicable — not a memory product","citation":null,"status":"not-applicable","tier":"T3"},"perf":{"value":"not applicable — does not compete on benchmarks","citation":null,"status":"not-applicable","tier":"T3"},"repro":{"value":"not applicable — not a research paper","citation":null,"status":"not-applicable","tier":"T3"},"code-release":{"value":"not applicable — not a research paper","citation":null,"status":"not-applicable","tier":"T3"},"api-surface":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"latency":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"throughput":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"backend-storage":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"multi-tenancy":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"encryption":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"sso-rbac":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"embedding-model":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"consistency":{"value":"not applicable","citation":null,"status":"not-applicable","tier":"T3"},"versioning":{"value":"none","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"tombstoning":{"value":"not applicable","citation":null,"status":"not-applicable","tier":"T3"},"schema-evolution":{"value":"not applicable — fixed evaluation dataset","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"namespace":{"value":"not applicable","citation":null,"status":"not-applicable","tier":"T3"},"contradiction":{"value":"not applicable","citation":null,"status":"not-applicable","tier":"T3"},"forgetting":{"value":"not applicable","citation":null,"status":"not-applicable","tier":"T3"},"mcp-support":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"a2a-support":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"otel":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"webhooks":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"import-export":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"integration-count":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"orchestration":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"programmatic-control":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"vendor-benchmarks":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-06"},"pricing-specifics":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"agent-abstraction":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"memory-primitives":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"llm-lock":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"runtimes":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"session-handling":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"validated-verticals":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"time-to-running":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"anti-fit":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"optimised-for":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"adjacent-infrastructure":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"pros":{"value":"Original needle-in-a-haystack benchmark — defined the long-context recall test paradigm.","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"cons":{"value":"Single-pattern test; commercial models now ace it; less informative for modern memory architectures.","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"links":{"value":"GitHub gkamradt","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"obs-langsmith":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-opentelemetry":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-datadog":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-helicone":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-weave":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-langfuse":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-arize":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-custom":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-token-budget":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-prompt-caching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-semantic-caching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-batching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-model-routing":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-streaming-only":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-observability-cost-attribution":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-langsmith-evals":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-braintrust":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-weights-and-biases-agent":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-helicone-evals":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-custom-test-harness":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-human-loop":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-production-traffic-replay":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"commit-trajectory":{"value":"[{\"ym\":\"2023-11\",\"cum\":9},{\"ym\":\"2023-12\",\"cum\":15},{\"ym\":\"2024-02\",\"cum\":16},{\"ym\":\"2024-03\",\"cum\":73},{\"ym\":\"2024-04\",\"cum\":75}]","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"citation-trajectory":{"value":"not applicable — non-paper row","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"download-trajectory":{"value":"not applicable — not published as a package","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"cost-input-usd-per-mtok":{"value":"0","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"cost-output-usd-per-mtok":{"value":"0","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"cost-tier":{"value":"free","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"cost-pricing-model":{"value":"free-tier","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"cost-last-verified":{"value":"2026-06-29","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack","status":"real-data","tier":"T1","source_class":"repo"},"capability-composite-score":{"value":"not applicable — benchmark / evaluation tool, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-band":{"value":"not applicable — benchmark / evaluation tool, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-benchmark-sources":{"value":"not applicable — benchmark / evaluation tool, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-last-verified":{"value":"not applicable — benchmark / evaluation tool, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"use-case-tags":{"value":"not applicable — benchmark, not a deployable system","citation":null,"status":"not-applicable","tier":"T3"},"use-case-anti-tags":{"value":"not applicable — benchmark, not a deployable system","citation":null,"status":"not-applicable","tier":"T3"},"adoption-accelerator":{"value":"","citation":null,"status":"no-data","tier":"T3"},"architecture-deployment-locus":{"value":"","citation":null,"status":"no-data","tier":"T3"},"licensing-bucket":{"value":"open-source","citation":"https://github.com/gkamradt/LLMTest_NeedleInAHaystack/blob/main/LICENSE","status":"real-data","tier":"T1","source_class":"repo"},"positioning-platform-vs-product":{"value":"","citation":null,"status":"no-data","tier":"T3"},"taxonomy-three-layer-rollup":{"value":"agent-infra","citation":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/docs/schema/section-to-three-layer-rollup.json","status":"real-data","tier":"T1","source_class":"repo"},"developer-activity-opendigger":{"value":"{\"activity\":1.49,\"as_of\":\"2025-10\",\"openrank_12mo\":1.8,\"openrank_current\":0.67,\"participants\":1}","citation":"https://oss.open-digger.cn/github/gkamradt/LLMTest_NeedleInAHaystack/openrank.json","status":"real-data","tier":"T2","last_verified_at":"2026-10-28","source_class":"third-party"},"freshness-date":{"value":"2026-05-14","citation":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/niah-needle-in-a-haystack--gh-gkamradt-llmtest-needleinahaystack","status":"real-data","tier":"T2","source_class":"catalog"},"compliance-certifications":{"value":"","citation":null,"status":"no-data","tier":"T3"},"sdk-languages":{"value":"","citation":null,"status":"no-data","tier":"T3"},"protocol-support":{"value":"","citation":null,"status":"no-data","tier":"T3"},"maturity":{"value":"","citation":null,"status":"no-data","tier":"T3"}},"corroboration":{"cited_cells":25,"third_party_cells":1},"edges":{"outgoing":[],"incoming":[{"source":"ruler--arxiv-2404-06654","target":"niah-needle-in-a-haystack--gh-gkamradt-llmtest-needleinahaystack","type":"extends","evidence":"Extends NIAH with multi-needle retrieval, multi-hop entity tracing, aggregation, QA — configurable for arbitrary length / difficulty.","citation":"https://arxiv.org/abs/2404.06654"}]},"history":[],"license":"CC-BY-4.0","source":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/data/landscape.json"}